Key Intelligent Pesticide Prescription Spraying Technologies for the Control of Pests, Diseases, and Weeds: A Review

Abstract

In modern agriculture, plant protection is the key to ensuring crop health and improving yields. Intelligent pesticide prescription spraying (IPPS) technologies monitor, diagnose, and make scientific decisions about pests, diseases, and weeds; formulate personalized and precision control plans; and prevent and control pests through the use of intelligent equipment. This study discusses key IPSS technologies from four perspectives: target information acquisition, information processing, pesticide prescription spraying, and implementation and control. In the target information acquisition section, target identification technologies based on images, remote sensing, acoustic waves, and electronic nose are introduced. In the information processing section, information processing methods such as information pre-processing, feature extraction, pest and disease identification, bioinformatics analysis, and time series data are addressed. In the pesticide prescription spraying section, the impact of pesticide selection, dose calculation, spraying time, and method on the resulting effect and the formulation of prescription pesticide spraying in a certain area are explored. In the implement and control section, vehicle automatic control technology, precision spraying technology, and droplet characteristic control technology and their applications are studied. In addition, this study discusses the future development prospectives of IPPS technologies, including multifunctional target information acquisition systems, decision-support systems based on generative AI, and the development of precision intelligent sprayers. The advancement of these technologies will enhance agricultural productivity in a more efficient, environmentally sustainable manner.

1. Introduction

Controlling pests, diseases, and weeds in modern agricultural production is key to ensuring healthy crop growth and improving product yield and quality. With changes in the ecological environment and continuous progress in agricultural production, the types of pests, diseases, and weeds and their occurrence patterns are also changing, bringing new challenges. While pesticide spraying is still the most effective and important measure of controlling pests, diseases, and weeds, spraying chemical pesticides can cause environmental pollution and result in pesticide residues in agricultural products.

The research and application of the key technologies for intelligent pesticide prescription spraying (IPPS) are significant for improving efficiency and precision in controlling pests, diseases, and weeds. These technologies involve the cross-disciplinary integration of fields such as modern information technology, biotechnology, mechanical and electronic engineering, botany, and pesticide science. The rapid development of technologies such as the Internet of Things (IoT), big data, and AIhas also facilitated significant advances in the research and application of IPPS technologies. The timeline of IPPS development is shown in Figure 1. This technological evolution has transformed IPPS technologies from simple mechanical applications to modern, sophisticated, integrated systems that combine multiple technologies for precise, efficient, and environmentally friendly pest management.

Intelligent monitoring refers to the automated and continuous surveillance of agricultural conditions using advanced technologies with sensors and data analysis systems. Through remote sensing technology and drones, the intelligent monitoring of farmland can provide real-time information on the occurrence and development of pests, diseases, and weeds. Big data and artificial intelligence technologies are employed to analyze patterns and trends in the occurrence of pests, diseases, and weeds, thereby providing a scientific basis for control decisions. IPPS must be precisely aligned with the objective and minimize side effects on human health, non-target organisms, and the environment by avoiding excessive doses, reducing application frequency, or employing fractional applications. It is essential that the associated risk to vegetation remains acceptable and does not increase the risk of resistance development in harmful organism populations [1].

While previous studies have significantly contributed to individual aspects of IPPS technologies, several important gaps remain in the existing literature. First, most studies focus on single technological components (such as image recognition and spraying systems) rather than comprehensively analyzing the entire IPPS system integration. Second, there is a limited systematic analysis of how different technologies interact and complement each other within the IPPS framework. Third, existing reviews often lack a detailed discussion of the practical challenges in implementing IPPS technologies across different agricultural contexts. Fourth, insufficient attention has been paid to integrating emerging technologies, such as generative AI and edge computing, into IPPS systems. Finally, previous studies have not adequately addressed how IPPS technologies can be optimized for different scales of agricultural operations, from small farms to large commercial operations. This study addresses these gaps by comprehensively analyzing IPPS technologies from a system-level perspective, examining technological integration and practical implementation challenges.

This study focuses on the key technologies of IPPS for pest, disease, and weed control, including intelligent monitoring technology; accurate diagnostic technology for pests, diseases, and weeds; intelligent decision-making technology; and advanced pesticide application technology. The objective is to develop personalized and precise control programs that provide scientific, efficient, and environmentally sustainable solutions for managing pests, diseases, and weeds in agricultural production. By analyzing and summarizing these key technologies, we hope to provide more accurate and intelligent pest and weed control strategies for agricultural production so that agriculture can be greener, smarter, and more efficient. By utilizing advanced application equipment to implement a comprehensive suite of technical systems, IPPS technologies markedly improve the efficiency and effectiveness of pest, disease, and weed control, reduce pesticide residues, protect the ecological environment, reduce agricultural production costs, and increase farmers’ income.

The implementation of IPPS technologies still faces several significant challenges. These include scalability issues when deploying across large agricultural areas, substantial initial investment costs for equipment and infrastructure, and potential environmental concerns, such as electromagnetic interference from sensors and electronic devices. Additionally, the complexity of integrating multiple technologies and the need for specialized training for farmers pose practical challenges to widespread adoption. Understanding and addressing these challenges are crucial for implementing IPPS technologies in modern agriculture. Therefore, this study proposes future research directions for IPPS technology.

2. Analysis of IPPS Process and Key Technologies

Figure 2 illustrates the logical sequence of pesticide prescription spraying. First, the relevant information regarding the target plant (images, spectral information, acoustic signals, etc.) must be obtained. Second, the relevant data must be preprocessed to improve quality and quantity. Third, information parsing techniques should be employed to analyze the preprocessed data and determine the classification and severity of pests and diseases affecting the target plant. Fourth, pesticide spraying prescriptions (usage, dosage, and precautions) should be designed based on the plant’s defense mechanisms and past disease data. Fifth, to ensure that sprayers can accurately reach the designated location and independently complete the spraying task, they must integrate navigation positioning with autonomous driving technology. Finally, various precise pesticide spraying techniques must be adopted to increase efficiency and reduce pesticide usage.

By analyzing the logical sequence diagram and the key IPPS technologies for pest, disease, and weed control, we conclude that IPPS technologies should include four layers, as shown in Figure 3. The first layer is the target information acquisition layer. This layer employs images, spectra, and other information acquisition tools to obtain information regarding the canopy and health state of target plants. The second layer is the information processing layer. This layer improves the quality and quantity of data and derives the corresponding characteristic parameters through various preprocessing and information analysis techniques. It also combines bioinformatics, molecular biology, and other technologies to comprehensively analyze pest, disease, and weed categories, distribution, and severity. The third layer is the pesticide prescription spraying layer. This layer is based on the type, distribution, and severity of pests, diseases, and weeds used to formulate the prescription. It aims to achieve specialized treatment of specific pests and precise pesticide spraying. At the same time, this layer also builds databases, including those for pest and weed information and pesticide classification data. These databases provide data support for the pesticide spraying model and ensure that the generated prescriptions are scientific. The fourth layer is the implement and control layer, which can implement precise on-target variable flow rate pesticide spraying techniques based on the prescription map generated by the target information, such as the plants’ canopy volume size and density.

3. Target Information Acquisition Layer

The target information acquisition layer includes common target information acquisition systems, such as machine vision, remote sensing, acoustic wave, and electronic nose, and carrying platforms for different target information acquisition devices. Vehicles are the most traditional image and spectral information acquisition device carriers due to their relatively low cost, versatility across various settings, and substantial expansion capabilities [2], enabling the integration of speed, flow, and pressure sensors [3] as well as laser sensors [4]. Remote sensing systems comprise remote sensing platforms, sensors, information transmission devices, digital or image processing equipment, and other related technologies [5]. Compared with traditional satellite remote sensing monitoring platforms, UAVs can operate at lower altitudes (80–400 m), offset the effects of extreme weather and cloud cover [6], achieve fast and accurate acquisition of high-precision images [7,8,9], and advance agricultural production toward superior quality, efficiency, safety, informatization, and intelligence [10]. This positions UAVs as a crucial tool for large-scale monitoring of pests, diseases, and weeds in the future [11].

3.1. Image-Based Target Information Acquisition Technology

To achieve the accuracy and reliability of precision pesticide spraying, it is necessary to obtain relevant plant damage information in a targeted manner to identify and locate pests, diseases, and weeds. Plants are infested by different pests, diseases, and weeds in different growth periods. Therefore, it is necessary to collect image sets of target plants susceptible to pests, diseases, and weeds in different periods and adequately train the model to improve the generalization ability and build a model that can accurately identify different pests, diseases, and weeds. Mimic weeds and several plants exhibit similarities in color and appearance, rendering standard methods inadequate for achieving high recognition accuracy. Therefore, image-based target information acquisition technology needs to improve the accuracy of crop and weed discrimination through various algorithms, even after collecting images of an area.

Image acquisition technology acquires high-quality images through various equipment and methods, which are simple and easy to operate and can provide strong technical support for the early identification and precise control of pests, diseases, and weeds. Commonly used devices include digital cameras, high-definition cameras carried by UAVs [12], automatic camera equipment fixed in the field, and high-precision scanning equipment. Digital cameras and fixed camera equipment usually have high resolution and good sensitivity and are suitable for working under various weather and light conditions. By shooting under sufficient light and acquiring images from different angles and distances, clear and comprehensive information can be obtained to support subsequent image analysis and identification of pests, diseases, and weeds. UAVs equipped with high-definition cameras are flexible and able to move quickly, making them suitable for large-scale image acquisition. UAVs can take pictures at different heights and angles, providing image data from multiple viewpoints and boosting precision agriculture. High-precision scanning equipment is mainly used to scan targets such as victim plant leaves to obtain high-resolution images. The scanning process must ensure uniform lighting to avoid reflections or shadows that affect image quality [13,14,15,16,17]. The types of equipment include stationary scanners, portable scanning equipment, and UAV scanning equipment.

3.1.1. Color

After some plants become diseased, they will produce disease spots that are different in color from the plants themselves [18], and the color of weeds often differs from the color of crops. Therefore, after collecting images of diseased plants and healthy plants (or weeds and crops), it is possible to judge whether the crop is diseased or identify weeds by comparing the RGB (Red, Green, Blue) or HSB (Hue, Saturation, Brightness) components of different images.

For example, when cucumber grows normally, there is a white horizontal line on the leading edge of the stem and leaves, and the surface of the leaves is in the form of a serrated triangle. When cucumber suffers from powdery mildew, the initial leaf color ranges from white to grayish-white, and in severe cases, the whole leaf wilts. When it suffers from spot blotch, yellowish or grayish-white spots can be observed on the leaf’s surface [19]. While UAVs are not typically used in greenhouse environments where cucumbers are often grown due to climate change, stationary or portable imaging systems can effectively monitor plant health.

3.1.2. Morphology

When plants are attacked by different pests, diseases, and weeds at different growth periods, the leaves will show different shapes and sizes of spots, which can be analyzed by comparing them with the normal leaves to find out which diseases plants suffer from or which pests are affecting them.

3.1.3. Texture

Texture-based identification of pests and diseases combines image processing, texture analysis, and machine learning techniques to identify and classify pests and diseases by analyzing texture features on the surface of plants or pests.

For example, the pectinate setae on the dorsal plate of the abdomen of Zeugodacus cucurbitae (Coquillett) are key textural features that can be recognized by machine vision and image processing techniques to provide a basis for pest control [20]. The textural characteristics of target plants can be extracted by preprocessing and segmenting images and then detected using the random forest model, which can solve low accuracy, overfitting, and high error rates [21].

3.1.4. Multiple Features

Multi-feature-based identification of pests, diseases, and weeds is a comprehensive approach that utilizes multiple data features and advanced machine learning techniques to improve the accuracy and efficiency of identification. This process combines image processing, sensor data analysis, and deep learning models using multiple sensors (e.g., RGB cameras, thermal imagers, and spectral cameras) to capture different data types from which multiple features, such as color, shape, texture, and spectrum, are extracted. These data are fused into a comprehensive feature set and subsequently fed into deep learning models (e.g., convolutional neural networks (CNNs)) or other algorithms (e.g., random forest and support vector machines) for training. By learning from large amounts of labeled data, these models can identify and classify various pests, diseases, and weeds more comprehensively and accurately, thus providing more effective decision support for integrated pest management (IPM).

For example, the color and shape of wormholes can be simultaneously analyzed as feature parameters, and the ratio of insect pest occurrence area to leaf area can be defined as an index for determining the severity of insect pests to achieve accurate determination of insect pests and provide a reference for precise pesticide spraying [22]. The color difference algorithm can also be used to isolate the diseased area of the target plant, and the diseases can be classified by combining the color histogram and texture features [23].

3.2. Target Information Acquisition Technology Based on Remote Sensing

As shown in Figure 4 [24,25,26], as a non-contact, long-range detection technology, the sensors loaded on the remote sensing platform can detect and receive electromagnetic waves emitted and reflected by different objects on the ground surface, which are converted into raw images according to a certain law and then transmitted to the ground-based computing processing center to derive the characteristic information of the target plants, including the canopy and diseases [26], to efficiently obtain agricultural information on pests, diseases, and weeds. In controlling possible pests, diseases, and weeds, satellite remote sensing has many advantages, such as a large monitoring area [26] and sufficient spectral information [27], which can realize the dynamic monitoring of pests, diseases, and weeds on a large scale. It can also analyze the relationship between the development pattern of pests, diseases, and weeds and the environment, providing a scientific basis for prevention and control initiatives in advance [28,29,30].

3.2.1. Multispectral

Multispectral remote sensing techniques analyze surface features by capturing spectral information at different wavelengths. Different plant statuses, such as healthy, infested by pests and weeds, water shortage, etc., reflect and absorb different wavelengths of light, resulting in changes in the spectral features that reflect the health of the vegetation [1]. By analyzing these spectral characteristics indicators, such as the Normalized Difference Vegetation Index (NDVI) [31], Ratio Vegetation Index (RVI) [32], and Normalized Difference Water Index (NDWI) [33], we were able to determine the health status of the vegetation and identify and classify pests, diseases, and weeds. Multispectral remote sensing is commonly used to monitor and assess pests, diseases, and weeds and identify potential problems before they cause significant losses. Figure 5 shows a schematic diagram of multispectral remote sensing used to identify trees and weeds. Note that t01 to t06 denote the identified tree 1 through tree 6, respectively.

3.2.2. Hyperspectral

Hyperspectral remote sensing technology can capture more detailed and broader spectral information than multispectral remote sensing, providing more spectral details and features. Hyperspectral remote sensing technology enhances the accuracy and reliability of target identification by capturing the reflectance or emission spectra of surface materials in a large number of consecutive narrow bands, resulting in a spectral profile of tens to hundreds of bands for each pixel point [34]. When pests infest plant leaves, their biochemical and structural properties change, which affects their spectral reflectance. These changes can be analyzed to identify and monitor pests, diseases, and weeds [35]. Hyperspectral remote sensing is suitable for accurately identifying and monitoring specific pests, weeds, and diseases. However, hyperspectral remote sensing involves a large amount of data, making processing costs high.

3.2.3. Near-Infrared

Near-infrared (NIR) remote sensing technology mainly uses the reflective properties of plant leaves to infrared light to monitor plant health [14]. Healthy plant leaves absorb a large amount of visible light and reflect a large amount of near-infrared light due to their rich chlorophyll content [15]. When pests, diseases, and weeds attack plants, the chlorophyll content decreases, decreasing the reflectance of near-infrared light, and the infested plants can be identified by monitoring this change [16,34]. Near-infrared remote sensing technology can cover a wide area and quickly obtain information on the health status of crops over large areas. However, when the pests are unevenly distributed or in the early stages of infestation, infrared remote sensing technology is insufficient to identify small-scale or early pest and weed infestations due to spatial resolution limitations.

3.2.4. Thermal Infrared

Thermal infrared remote sensing technology is based on the changes in surface temperature of plant leaves [36,37] and can be used to monitor plants’ transpiration and health status by capturing changes in surface temperature [38]. Plants release water through transpiration to regulate body temperature. When plants are infested, and transpiration is affected, the changes in leaf surface temperature can be sensed to monitor pests, diseases, and weeds.

3.2.5. Synthetic Aperture Radar

Synthetic Aperture Radar (SAR) technology utilizes the ability of radar waves to penetrate clouds and parts of vegetation by transmitting electromagnetic waves to the ground and then receiving the signals reflected. Analyzing these reflected signals can obtain information about ground targets [39]. Different ground substances and conditions (e.g., humidity, structure, material, etc.) affect the reflective properties of radar waves. By analyzing SAR image data, the type of pest and weed infestations can be identified [40]. Because microwaves can penetrate clouds and a certain degree of vegetation cover, SAR is suitable for all-weather, all-day monitoring. However, SAR has problems such as difficulty in interpretation.

3.2.6. Unmanned Aerial Vehicles

Remote sensing equipment carried by UAVs is increasingly used in precision agriculture and pest and weed management due to its low cost, high flexibility, and high resolution. UAVs can carry cameras [41,42] and sensors such as multispectral, hyperspectral [43], and thermal infrared sensors for pest, disease, and weed detection, monitoring, and assessment in localized areas. UAV remote sensing is particularly suitable for fine management and small-scale, high-precision monitoring of pests, diseases, and weeds [44].

3.2.7. Light Detection and Ranging

As a 3D remote sensing technology, Light Detection and Ranging (LiDAR) is used to obtain precise 3D positional information of targets, including tree height, canopy density, and canopy cover, by emitting laser pulses and measuring the time when these pulses are reflected from the target [45,46]. LiDAR has the advantage of acquiring high-precision data elevation models, digital surface models, orthophotos, digital line drawings, 3D scenes, and 3D model construction. It has the advantages of small environmental constraints, low operating costs, fast acquisition speed, and high data accuracy [47]. The information obtained through fluorescence LiDAR helps users to understand vegetation’s health and growth environment, thus identifying unfavorable conditions that may lead to pests, diseases, and weeds [17]. However, detecting fluorescence through dye powder-dusted insects would be technologically complex and costly under field conditions. Modern LiDAR technology that can incorporate spectrum distribution and the use of multiple wavelengths has the characteristics of being unrestricted by light conditions and having a strong penetration ability. However, this technology still has shortcomings, such as difficult data processing, high equipment costs, and difficulty interpreting.

LiDAR can be classified according to the type of signal form, detection mode, number of lines, functional use, scanning mode, laser light source, delivery platform, etc. The classification of LiDAR is shown in Figure 6.

The vehicle-mounted 2D laser scanner is used to acquire unilateral point cloud data of trees, and after coordinate transformation and discretization, the scale information related to the target plant is calculated to achieve online measurement of canopy volume in continuous/discontinuous scenarios of tree crowns and provide technical support for precision pesticide application [48]. Combining airborne laser and aerial multispectral data can automatically identify pest and weed outbreak areas and predict infestation probability.

3.3. Target Information Acquisition Technology Based on Acoustic Waves

Acoustic waves are mechanical waves that can propagate through air, liquids, and solids. Different substances and structures have different acoustic wave reflection, absorption, and transmission properties, which provide the basis for identification and detection. Acoustic wave-based target information collection technology detects and identifies crop pests, diseases, and weeds using acoustic wave properties.

Common acoustic detection methods include the following:

1. Accelerometers detect vibrations by measuring surface acceleration. Vibrations or impacts can be sensed in one or more axes. They are usually fixed on the plant surface and detect small vibrations generated by internal insect activity [49]. However, the application to mass cultivation is limited due to the impracticality of deploying sensors on millions of individual plants in large-scale agricultural settings;

2. Piezoelectric crystals are used to convert mechanical stress directly into an electrical signal. When stressed, the crystal generates a measurable electrical charge capable of capturing and converting acoustic waves or vibrations into electrical signals for detecting insect activity [50,51];

3. Acoustic probes with integrated piezoelectric sensors or accelerometers can be inserted into soil, crops, or trees to record and analyze acoustic signals generated by insect activity. Different insect pests are automatically identified by signal processing algorithms [52];

4. The principle of microphone pest identification is mainly based on impact acoustic (IA) measurements. It collects and analyzes the acoustic signals generated when crop samples are impacted with specific materials (e.g., steel plates) and captures them using a high-sensitivity microphone. Subsequently, the frequency and amplitude characteristics of the signals are input into the neural network for analysis to determine whether the crop is infested and its severity [53];

5. Ultrasonic waves generated by an ultrasonic transducer can detect insect pests in trees. Time of flight (TOF) is a parameter that measures the time it takes for an acoustic wave to propagate a certain distance in a medium. TOF is overly sensitive to defects in trees. By measuring the TOF of acoustic waves, ultrasonic transducers can effectively detect insect pests in a tree and assess the overall health of trees [54].

These acoustic detection methods perform well in laboratory environments but face challenges in practical applications such as background noise and wind interference. In addition, the installation of sensors may damage samples, and signal interpretation may be complicated.

3.4. Target Information Acquisition Technology Based on Electronic Nose

Target information collection technology based on an electronic nose (e-nose) is a diagnostic method of detecting and identifying various plant pests, diseases, and weeds using e-nose devices. The e-nose simulates a biological olfactory system and consists of a sensor array, a signal conditioning circuit, and a pattern recognition algorithm. Plants release specific volatile organic compounds (VOCs) when infested with pests and diseases or confronted with weeds [55,56]. When VOCs pass through the sensor array, they cause reversible physicochemical changes in the sensing materials, which alter electrical properties such as resistance and potential.

In diagnosing early aphid infestation in greenhouse tomato plants, VOCs released from healthy and aphid-infested tomato plants can be infested and analyzed using e-noses equipped with multiple gas sensors and data acquisition systems to identify aphid infestation before the plants show visible symptoms [57]. However, the diagnostic method in controlled greenhouse environments might not apply and needs modification for open spaces.

A portable e-nose was developed to assess the damage caused by cotton pests, including stink bugs, by extracting VOCs from the headspace of a cotton boll using carbon black-polymer composite sensors. The device can classify the cotton as damaged or undamaged by differentiating VOCs released from undamaged or damaged bolls. However, environmental factors may affect sensor response, so it would be beneficial to train the device in the same environmental conditions to minimize the effects of these factors [58].

Systemic resistance-induced defense-associated VOCs significantly affect the VOC signature of diseased plants. Volatile plant defense and protective compounds include terpenoids, essential oils, plant hormones, secondary metabolites, other metabolic byproducts, and compounds associated with cell damage. The changes in plant VOC emissions associated with plant diseases eventually led to collective VOC analysis using sensor arrays in e-noses [59]. The e-nose has a low threshold for detecting VOCs and does not require physical contact or damage to the plant. In addition, e-nose systems have the advantages of being low in cost and simple to use, with no extensive training required, fast results, convenient portability, and high accuracy [60]. However, other environmental odors may interfere with the detection results and require complex algorithms for data analysis.

3.5. Target Information Acquisition Technology Based on IoT

IoT technology in agriculture refers to the application of IoT sensors [61,62] and systems originally developed for various sensors, wireless communication technologies (e.g., LoRa, NB-IoT, 4G/5G, etc.), and data processing platforms. These technologies are applied to achieve real-time monitoring, intelligent analysis, and precise management of the agricultural production environment and crop growth conditions [63,64]. This enables precise management and intelligent control of agricultural production [65], improving efficiency and product quality, reducing environmental pollution, saving resources, and lowering costs [66]. Agricultural IoT technology involves collecting, storing, processing, and analyzing agricultural information data, relying on cloud computing technology, big data technology, edge computing technology [67,68], etc. With the continuous development of technology and reduction in costs, agricultural IoT technology will be more widely used in IPPS technologies in the future.

IPPS would not be possible without IoT sensors. Sensors are used to gather and measure different factors and variables of environments that could affect crop yield [69] and monitor anomalies, weeds, diseases, pests, and crop mapping with the help of spatial, spectral, and temporal resolution [70,71,72].

The agricultural IoT technology is deeply integrated with the above-mentioned technologies. The strengths and weaknesses of different target collection technologies were analyzed, as shown in Table 1.

4. Information Processing Layer

The information processing layer includes preprocessing techniques to improve the quality of the dataset and increase the number of samples in the dataset; information analysis techniques to analyze the relationship between various indicators and features and pests, diseases, and weeds; and model improvement techniques to improve the generalization ability and accuracy of the model. In addition, a variety of methods, such as deep learning, image recognition, geographic information system (GIS), time series analysis, data mining, and molecular biology and chemical inducer detection, have been widely used, which not only improve the accuracy and real-time performance of the identification of pests, diseases, and weeds but also provide a scientific basis in the development of control strategies, making an important contribution to the sustainable development of modern agriculture.

4.1. Information Preprocessing Techniques

Information preprocessing techniques in pest, disease, and weed identification processes acquire target images or data to improve identification accuracy and efficiency. These techniques include but are not limited to image preprocessing, data cleaning, data enhancement, and data conversion.

1. Image preprocessing is a critical step in identifying pests, diseases, and weeds, and its main purpose is to improve the image quality and make it more suitable for subsequent processing steps [73,74] to increase the correctness of identification. Common image preprocessing techniques include image enhancement [75], image denoising [76,77], and image segmentation [78,79];

2. Data cleaning is a key step in data preprocessing, and the cleaned data are more suitable for analysis and modeling, improving the accuracy and reliability of pest, disease, and weed identification and classification. It includes using statistical methods to identify outliers, remove duplicate data, and remove or fill in missing values;

3. Data enhancement is a common technique used in the training process of deep learning models to generate new training samples by rotating [80], flipping, cropping, etc., plant images containing pests or disease spots, thus increasing the diversity of the data and improving the generalization ability of the model [81,82];

4. Data conversion is an important step in data preprocessing, which converts data into a format suitable for analysis and modeling. For example, data normalization is important when dealing with non-image data (e.g., temperature, humidity, soil pH, etc.) related to pests, diseases, and weeds. It aims to transform data from different sources to the same scale to eliminate the effect of data magnitude [83,84], and commonly used methods include maximum–minimum normalization and z-score normalization. When dealing with data with exponential growth, logarithmic transformation is often used to reduce the skewness of the data. When performing classification tasks, one-host encoding and label encoding are often used for processing, and they can convert categorical variables into binary vectors or integers.

In summary, information preprocessing techniques for pest, disease, and weed identification are complex processes that include multiple steps, such as image preprocessing, data normalization, feature extraction and selection, and data enhancement. These techniques can effectively improve the accuracy and efficiency of pest recognition.

4.2. Target Feature Extraction and Identification of Pests, Diseases, and Weeds

Target feature extraction involves identifying and utilizing key features to classify and identify pesticide spraying target information. Feature extraction is the process of converting raw data into a form that is more suitable for model processing. It uses data mining, deep learning, and image recognition. Additionally, feature selection selects the most useful parts from these features to reduce the model’s complexity and improve recognition efficiency [85]. Common features include color features [86], shape features [87,88], and texture features [89].

4.2.1. Data Mining

Data mining techniques play a vital role in target identification and prediction. Data mining is the process of extracting useful information and knowledge from a large amount of data, including various techniques such as statistics, machine learning, and pattern recognition. Using data mining techniques can help better elucidate and predict the occurrence of pests, diseases, and weeds so that more effective preventive and control measures can be taken [90,91].

Data mining technology application scenarios include automatically identifying pests, diseases, and weeds by analyzing plants’ images or other sensory data using image processing and pattern recognition techniques [92]. By analyzing historical pests, diseases, weeds, and related environmental factors (e.g., temperature, humidity, rainfall, etc.), machine learning models are used to predict the probability and severity of future infestation [93,94]. Combined with GIS and remote sensing techniques, the risk of pests, diseases, and weeds in a specific area can be analyzed to provide a reference for agricultural production [95,96].

Key data mining techniques include classification, regression, cluster analysis, and association rule mining.

Classification algorithms such as decision trees [97], random forest (RF) [98], and support vector machine (SVM) [99] are used to identify types of pests, diseases, and weeds. Regression algorithms such as linear regression [100] and ridge regression [101] are used to predict pest, disease, and weed severity.

The distribution pattern of pests, weeds, and diseases is analyzed through clustering algorithms (e.g., K-means, hierarchical clustering, etc.) to help decision makers formulate regional prevention and control strategies [102,103,104].

Association rule mining is important to ascertain the correlation between the occurrence of pests, diseases, and weeds and the underlying environmental factors. This knowledge is fundamental for developing and implementing effective pest, disease, and weed control strategies [105].

4.2.2. Deep Learning and Image Recognition

By using deep learning (DL) models such as convolutional neural networks (CNNs), features can be automatically extracted from plant images to achieve fast and accurate identification of various pests, diseases, and weeds [106,107]. This technology improves the efficiency and accuracy of recognition and enables real-time monitoring of large farmland areas, helping farmers identify and deal with problems promptly, thereby improving crop yield and quality.

In pest, disease, and weed identification and early warning systems, image recognition technology can automatically identify and classify target features using computer vision technology to interpret and understand the content of images [87,108]. Dynamic acquisition of crop morphology is more beneficial to real-time variable decisions of precise spraying operations in fields [109].

As a deep learning-based target detection algorithm, You Only Look Once (YOLO) uses a deep convolutional neural network (CNN) for target detection. The network architecture of YOLO usually includes multiple convolutional, pooling, and fully connected layers for feature extraction and target detection. YOLO is trained through an end-to-end approach that can simplify the design and implementation of the model, enabling it to efficiently perform target pest detection [110]. YOLO treats target detection as a regression problem rather than a classification problem. It predicts bounding box and category probabilities directly from the image. Unlike two-stage detection (e.g., R-CNN family), YOLO requires only one forward propagation to complete the agricultural disease detection [111].

The real-time detection capability of YOLO makes it well suited for enabling rapid identification and localization of pests, diseases, and weeds on crops [112,113] and early prediction of pests, diseases, and weeds [114]. Due to its single-stage detection nature, YOLO can operate efficiently in environments with limited computational resources, which is important for agricultural field detection [115]. YOLO can detect multiple pests, diseases, and weeds at the same time [116,117], which is useful for complex agricultural environments.

Compared to CNNs, some novel improved neural networks, such as the cascaded attention transformer network (CATNet) [118,119], generate adversarial-driven cross-aware network (GACNet) [120], and spatial, spectral, and texture-aware attention network (SSTNet) using hyperspectral images [121], have introduced attention mechanisms, improved the efficiency of target feature extraction, and achieved higher recognition accuracy.

After data preprocessing and feature extraction, a suitable model is selected for training so that the model can accurately identify the types of pests, diseases, and weeds. However, limited by the amount of training samples and time cost, the training efficiency can be improved by utilizing transfer and incremental learning. Transfer learning utilizes models pre-trained on other large datasets as a starting point, and they are fine-tuned for specific pest identification tasks [111,122]. Over time, incremental learning continuously incorporates newly collected data into the training set and continues to train the model to improve its accuracy and adaptability [123,124].

4.3. Analysis of Target Biological Characteristics

In addition to traditional target identification methods, molecular biology and chemical inducer detection technologies can increasingly provide new, in-depth ways to understand pests, diseases, and weeds at the microscopic genetic and metabolic levels with the rapid development of biotechnology. These methods enable earlier and more precise identification of targets and provide insights into the physiological mechanisms of pests, diseases, and weeds as well as the plant defense responses, thus providing new perspectives and bases for precision pesticide spraying.

4.3.1. Target Identification Technology Based on Molecular Biology

Target identification techniques based on molecular biology methods mainly aim to identify and study the key biological characteristics of pathogens, pests, and weeds that cause crop damage to develop more effective control strategies. The common molecular biology target identification methods include genomics and transcriptomics analysis, proteomics and metabolomics, molecular marker technology, and gene editing techniques.

1. Detecting the genome [125] and transcriptome [126] of pathogens, pests, or weeds can identify key genes or gene expression patterns associated with developing diseases, pests, or weeds. This information is essential for understanding the pests’ biology, the infestation process, and the interaction mechanism with the host plant;

2. The proteomics and metabolomics techniques involve studying proteins [125] and metabolites [126,127,128] of pathogens, pests or weeds. New intervention points can be discovered by identifying key proteins and metabolic pathways;

3. Specific genes or genomic regions associated with diseases, pests, or weeds can be traced and identified using molecular marker technology. This helps to understand the genetic diversity of pests and pathogens and their resistance mechanisms to pesticides [129,130];

4. Gene editing techniques, such as CRISPR-Cas9, can be used to knock out or modify specific genes of pathogens, pests, or weeds to study the function of these genes and their role in the physiological activities of the organism. This helps to validate potential control targets [131,132,133].

4.3.2. Chemical Inducer Detection

The discovery and identification of specific molecules or biological processes that can be used to control pathogens, pests, or weeds is also a key strategy in target identification technology. Chemical inducer detection technology involves identifying and analyzing specific chemicals produced by plants when infested by pathogens or pests or subjected to other stressful conditions. These chemicals, often called phytohormones or signaling molecules, such as jasmonic acid, salicylic acid, and ethylene, play a key role in the plant’s defense response. The main methods of chemical inducer detection techniques include high-performance liquid chromatography (HPLC)–ultra-high performance liquid chromatography (UPLC), gas chromatography–mass spectrometry (GC-MS), liquid chromatography–mass spectrometry (LC-MS) and enzyme-linked immunosorbent assay (ELISA).

1. HPLC [134]-UPLC [135] is the most commonly used chemical analysis technique. It can accurately separate, identify, and quantitatively analyze plant chemical inducers. Through HPLC-UPLC, it is possible to identify specific compounds released by plants when they are infested and thus understand the role of these compounds in plant defense;

2. GC-MS is another powerful analytical technique that is particularly suitable for the analysis of VOCs released by plants under attack by pests, diseases, and weeds that may serve to attract natural enemies or suppress pests [136,137];

3. LC-MS combines liquid chromatography’s separation capability with mass spectrometry’s identification capability and is suitable for analyzing non-volatile and polar compounds. LC-MS can detect and identify secondary metabolites and signaling molecules in the plant body, which play a key role in plant defense responses [138];

4. ELISA is an antibody-based biochemical technique that can be used for the specific detection and quantitative analysis of plant hormones and other protein markers. The sensitivity and specificity of ELISA make it ideal for detecting plant signaling molecules at low concentrations [139].

These chemical inducer detection techniques allow for a deeper understanding of plant defense mechanisms, which can lead to the discovery and development of new and more effective pest, disease, and weed control strategies. These strategies may include the development of a chemical inducer that stimulates or enhances the plant’s defense response or the design of synthetic compounds that target specific chemical inducers to interfere with the physiological processes of the pests or pathogens.

The strengths and weaknesses of target biological characteristics analysis compared to traditional and DL methods are shown in Table 2.

4.4. Time Series Analysis for Pest and Disease Prediction

GIS can collect, manage, and analyze geospatial data [140]. GIS uses satellites, UAVs, and ground carriers to collect information on agricultural conditions and analyze and process them using image processing, data fusion, time series analysis, and spatial analysis. Then, combining past data and current information, GIS is used to build a prediction model for pests, diseases, and weeds and assess future risks. By analyzing the potential impacts of pests, diseases, and weeds on crop yield and quality [141], targeted pest, disease, and weed control measures are developed based on the results of GIS analysis [142].

Time series analysis is a statistical method for analyzing chronological data points to understand past behavior, predict future trends, or identify meaningful patterns from data.

The application of time series analysis techniques in target identification involves using time series data to monitor and identify pests, diseases, and weeds. Time series data can be temperature, humidity, light, plant growth indicators, etc., usually collected through sensors over time. Time series analysis can help predict the probability and severity of pests, diseases, and weeds over time by analyzing target data. This is extremely helpful in developing preventive and control measures in advance. In addition, environmental factors such as temperature, humidity, and rainfall directly impact the occurrence of pests, diseases, and weeds. Time series analysis can be used to analyze the relationship between these environmental factors and the occurrence of pests, weeds, and diseases, thus predicting the risk of infestation under specific environmental conditions.

Common technical approaches to time series analysis include autoregressive (AR) and moving average (MA) models [143]. Some models are extensions of these two models, including the following:

1. The autoregressive moving average (ARMA) model combines the features of AR and MA models, which is used as a statistical model for analyzing and forecasting time series data and is suitable for analyzing smooth time series data. The ARMA model allows for modeling quantitative changes in insect populations and analyzing population growth, decline, and cyclical fluctuations. While traditional population dynamics models are usually deterministic, ARMA models can introduce random factors to better simulate the effects of unpredictable factors in the real environment on the population. ARMA models can help quantify the strength and stability of population regulation, particularly density-dependence and feedback mechanisms. ARMA models can identify and integrate time-lagged and seasonal patterns, which are essential for accurately predicting the occurrence and development of pests, diseases, and weeds. Through these features, ARMA models play an important role in identifying pests, diseases, and weeds, helping researchers and farmers better understand and manage the dynamics of insect populations [144];

2. The autoregressive integrated sliding average (ARIMA) model is an extension of the ARMA model that handles non-stationary time series data. For example, Trialeurodes vaporariorum is a major pest of greenhouse crops and can transmit various plant viruses, and traditional pesticide spraying methods are costly and may negatively impact the environment and farmers’ health. Models based on time series analysis (ARIMA and ARIMAX; X is the external variable) were developed to predict Trialeurodes vaporariorum population growth in greenhouses. Predicting changes in Trialeurodes vaporariorum populations helps farmers schedule pesticide spraying more efficiently. In contrast to the ARIMA model, which uses only Trialeurodes vaporariorum population data, the ARIMAX model combines Trialeurodes vaporariorum population and environmental data (e.g., temperature and humidity), which can predict population growth of Trialeurodes vaporariorum more effectively. Automating data collection and analysis enables farmers to manage pests in more timely and accurate ways, reduce pesticide usage, and improve the sustainability of agricultural production [145];

3. The seasonal autoregressive integrated moving average (SARIMA) model is an extension of the ARIMA model and is specifically designed to deal with data with distinct seasonal patterns. For example, the mango flea beetle is a major pest of mango in tropical and subtropical regions of India and can cause up to 100% yield loss. Using SARIMA to predict mango flea beetle populations can provide a timely and accurate advance prediction of mango flea beetle occurrence and provide a scientific basis for developing regional integrated pest management strategies. Applying the SARIMA model to pest, disease, and weed identification not only improves the accuracy of prediction but also provides farmers with a scientific decision-support tool that can help better cope with the challenges posed by climate change [146].

Effective timing prediction and possible epidemiological trends in pests, diseases, and weeds are the keys to control and management. Research on the growth and reproduction habits of pests, diseases, and weeds provides a basis for developing appropriate timing of control and prevention and analyzing the impact of different environmental conditions on pests, diseases, and weeds to determine their optimal growing environments. Combining IoT and big data analysis technology, real-time dynamic monitoring and warning systems can quickly respond once anomalies are detected. Together, these parts form a comprehensive framework for managing pests, diseases, and weeds, which helps increase crop yields and safeguard the ecological environment.

5. Pesticide Prescription Spraying Layer

The selection of pesticides, dose calculation, spraying time, and method are key factors in formulating prescriptions for pesticide spraying. These factors affect the economic efficiency of pesticide usage and relate to the sustainable management of the environment. By combining modern technologies such as geographic information, sensor technology, and computer vision, precision pesticide spraying can accurately manage different crops, pests, diseases, and weeds and their cycles of occurrence, thus achieving higher application efficiency and better ecological benefits.

5.1. The Relationship Between Plant Defense Mechanisms and IPPS

Plants have developed complex defense systems to resist pathogens, pests, and weeds over long periods of evolution. These mechanisms include physical, chemical, and induced defenses.

1. Physical defense means that the epidermal waxy layer [147,148], cuticle [149], and bark of plants can block the infestation of pathogens and insects. Some plants have thorns, spines, and prickles [150] that can physically stop herbivores from nibbling;

2. Chemical defense means that some plants produce chemicals such as alkaloids, terpenes, and phenols [151,152], which can poison or repel herbivorous insects. Some plants release VOCs when infested, attracting predators against herbivores [153];

3. Induced defense means that the whole plant activates defense mechanisms to increase resistance to the pathogen when a part of the plant is infested [154,155,156], known as systemic acquired resistance. In addition, plants transmit information through signaling molecules (e.g., jasmonic acid and salicylic acid) in the body to activate defense genes [157,158].

Based on crop growth and pest and weed infestation, etc., personalized prescriptions are developed. The main features include selecting pesticides according to the specific problems of the target, controlling the dose and spraying time precisely, reducing unnecessary use and cost, and reducing the environmental impact.

The relationship between plant defense mechanisms and IPPS is shown in Figure 7.

1. Plant defense mechanisms are the first line of defense, and studying these mechanisms can help develop resistant varieties and reduce pesticide dependence [159,160]. IPPS is a complementary tool to intervene when plant defenses are inadequate;

2. Understanding plant defense mechanisms can guide more information for IPPS decisions. For example, timely preventive application can be carried out by identifying the early signals of plant defense response;

3. Some pesticides can activate the plant’s defense mechanism, and reasonable IPPS can enhance the plant’s defense ability with some synergistic effect. Choosing the right spraying time and dosage can be combined with the plant’s natural defense response to improve the effectiveness of prevention and control;

4. Using plant defense mechanisms can reduce the usage of pesticides in the long term, which is conducive to the sustainable development of the agroecosystem. The combination of IPPS and defense mechanisms can lead to integrated pest management (IPM), which efficiently controls pests, diseases, and weeds while reducing the reliance on chemical pesticides and enhancing the natural defense capabilities of plants;

5. Excessive use of pesticides may interfere with normal plant defense mechanisms, and IPPS can minimize such interference.

The relationship between IPPS methods and plant defense mechanisms is dynamic and complex. A deeper understanding of precision agriculture prescription can help agricultural producers and researchers develop more effective and sustainable pest, disease, and weed management strategies. Combining targeted plants’ natural defenses with optimized pesticide application can achieve more precision, cost effectiveness, and environmentally friendly agricultural production.

5.2. Selection of Pesticide Formulations, Dose Calculation, and Usage Time

Different plant defense mechanisms may respond differently to different types of pesticides. The appropriate pesticide type selection is based on the specific defense mechanisms of the plant and the types of pests, diseases, and weeds [161]. If the plant relies mainly on induced defenses, selecting pesticides that activate these defense mechanisms may be necessary.

In order to achieve different efficacy, different pesticides need to be selected. Chemical insecticides were proven significantly more effective than biopesticides in a short timeframe. The efficacy period of biopesticides is significantly longer than that of chemical insecticides [162]. In addition, the environmental impact of the pesticides should be considered, and environmentally friendly and easily degradable pesticides should be selected as much as possible [38]. Long-term use of the same pesticide, leading to resistance to pests, diseases, and weeds, should also be avoided, and pesticides with different mechanisms of action should be rotated [163,164,165].

Precision pesticide spraying in agriculture involves precise control of the timing, method, dosage, and type of pesticide spraying. The recommended dosage in the pesticide instruction manual should be referred to first when arranging pesticide dosage. The dose can be adjusted according to the growth stage of the plant. Generally speaking, a lower dose is used in the early stage of plant growth and can be increased appropriately during the vigorous growth period [38]. The dose can be reduced when the pests, diseases, and weed infestation are mild. When serious, the dose must be increased, but it should not exceed the highest dose recommended in the pesticide instruction manual. Reducing the amount of pesticide used may be possible for varieties with greater resistance, thereby reducing environmental impact and costs. In addition, under unfavorable conditions such as high temperatures and drought, the amount of pesticides used should be appropriately reduced to minimize potential plant damage. In a word, the objective is to control pests, diseases, and weeds while simultaneously minimizing environmental damage [166].

The correct timing and methods of pesticide use are essential to ensure the pesticide’s effectiveness and minimize its impact on the environment [167].

Different pesticide spraying times affect where the pesticide goes and the amount of pesticide that leaches to the drains [168]. Different regions have different climatic gradients and field characteristics, so appropriate application times must be selected based on the field environment and local conditions [169,170]. In addition, pesticide spraying should avoid rainy or strong windy weather to reduce the loss and drift of the pesticide. Furthermore, high temperatures and strong sunlight may also affect the effectiveness of certain pesticides, so it is more appropriate to choose a cooler time in the morning or evening for pesticide spraying [170,171,172,173].

Understanding the life cycle of specific pests, diseases, and weeds is critical to determining the best application time. For example, when dealing with certain pests, the best time to apply may be when they are most active, so determining the best time to spray insecticides can ensure that pest populations are kept below economic loss levels [174]. On the other hand, for some diseases, the optimum time for pesticide spraying may be prior to the onset of the disease. For others, pesticide spraying may be required as soon as signs of the disease are detected.

Generative AI can assist in identifying the location and severity of pests, diseases, and weeds based on historical data and environmental parameters and choosing the most suitable pesticide while providing the optimal dose and usage timing.

5.3. Precautions for Pesticide Application

In order to use pesticides more accurately, efficiently, and sustainably, many precautions need to be taken.

1. Applicators should wear appropriate protective equipment, such as protective clothing, gloves, face masks, and goggles, to avoid direct contact with pesticides on the skin and in the eyes, and they should wash their hands and faces immediately after spraying. It is imperative that surplus pesticides and their packaging are disposed of appropriately. Furthermore, pesticide containers must not be used for any other purpose, and local regulations pertaining to pesticide waste disposal must be adhered to. Furthermore, gaining knowledge of first-aid procedures and familiarizing oneself with the details of emergency contacts is advisable. In addition, it is recommended to ensure the availability of water and soap in advance for washing after inadvertent contact;

2. It is inadvisable to undertake spraying operations during elevated pollinating insect activity, such as that observed in bees. In order to ensure the protection of non-target and beneficial organisms, due care must be exercised in this regard;

3. For some plants, pesticides can be applied directly to the plant roots through an irrigation system, which can improve the utilization of the pesticides [175,176], but root irrigation may pose a greater potential risk than spraying [177];

4. Pesticides can be injected directly into the plant for some large trees or specific crops to control pests or diseases. This method can significantly reduce the amounts of pesticides used and environmental pollution [178,179,180];

5. When two or more pesticides are mixed, there is a risk that their interactions may lead to reduced effectiveness or ineffectiveness. This is known as antagonism, which affects the control effect and may cause economic losses and environmental problems. For example, cyhalofop-butyl, a graminicide used to control rice postemergence weeds, is antagonized by some herbicides applied simultaneously [181]. In addition, spirodiclofen interacts with imidacloprid and appears antagonistic to the acaricidal effect of the Brevipalpus californicus when mixed [182]. Hence, pesticide spraying strategies should be adjusted according to the mechanism of pesticide resistance in pests, diseases, and weeds. Pesticides with different mechanisms of action should be rotated, or mixed spraying strategies should be used to slow down the development of resistance.

5.4. Pesticide Prescription Map

The core concept of pesticide spraying based on prescription maps is to use detailed spatial data to generate “prescription maps” that differentiate pesticide spraying according to the specific needs of different areas. The prescription map uses equipment (e.g., LiDAR, real-time kinematic, RTK, drones, etc.) to collect detailed data on a field or orchard, including topography, canopy characteristics, and vegetation conditions [183]. The collected data are converted into digital maps in GIS, which are analyzed by algorithms to generate 3D or 2D prescription maps for plant requirements in different regions. Differentiated pesticide spraying is carried out based on the prescription map. The pesticide spraying can be carried out using automated equipment (e.g., precision spraying drones [184] or self-driving tractors). During the application process, the spray volume and range are adjusted at any time through real-time data feedback and sensor monitoring to achieve the best results [185]. After pesticide spraying, the effect of pest control is evaluated through subsequent data collection and analysis to optimize the next round of application strategy.

The captured color images are first grayed, and then, the RGB model is converted to HSV. The maximum interclass variance method is used to perform dynamic threshold segmentation on the ultra-green feature gray-scale images to obtain the binary images of cotton and weeds, respectively. Then, the pesticide level and grid division are determined based on the weed center-of-mass coordinates and leaf area, and the prescription map is generated. The results of one study showed that a precision pesticide spraying system based on a prescription map can effectively improve pesticide utilization and reduce pesticide usage [186].

In areas with low plant vigor, the density of pest populations tends to be low as well, so a prescription map was designed to apply different dosages of insecticides in different areas according to the level of plant vigor to achieve the purpose of exterminating pests and reducing the number of insecticides at the same time [187].

By monitoring and analyzing the locust growing environment, the distribution of locusts can be analyzed and the distribution map adjusted according to the real-time status to create the locust infestation level zoning map. Then, combined with the actual situation of locust control in different regions, the aircraft precision prescription map of pesticide spraying and the ground precision prescription map of pesticide spraying, including the navigation track and variable pesticide spraying information, can achieve precise control of pesticide spraying over a large area and significantly reduce pesticide residue [188].

In one study, a mathematical model was established between crop canopy height and amount of pesticide spraying, the plant height information identified by LiDAR was transferred to the variable pesticide spraying system to generate the spray volume prescription map, and it was sent to the PWM controller, which changed the opening and closing of the solenoid valve in real time to change the spray volume, to achieve the purpose of precise variable pesticide spraying [189].

Overall, IPPS in agriculture effectively controls pests, diseases, and weeds through the integrated application of pesticide selection, dose calculation, and appropriate spraying time and method while minimizing the negative impact on the environment, greatly enhancing the effectiveness and utilization of pesticide use. At the same time, the use of GIS, sensor technology, automated equipment, and the application of UAVs, intelligent monitoring systems, and other modern tools to achieve differentiated precision pesticide spraying in different regions and plants will further improve the accuracy and efficiency of the pesticide spraying, significantly reducing the pollution of pesticides on the environment and waste. IPPS in agriculture will become a powerful driving force to promote the development of modern agriculture in a more efficient, environmentally friendly, and intelligent direction.

6. Implement and Control Layer

In the implement and control layer, navigation, positioning, automatic driving technology, precision spraying, and droplet characteristic control technology play an important role. Using navigation and positioning technology based on the global navigation satellite system (GNSS) and automatic driving technology can realize efficient and accurate intelligent plant protection operations. Precision spraying technology optimizes the use of pesticides and fertilizers through advanced sensors and control systems to safeguard plant health and environmental safety. Meanwhile, droplet characteristic control technology improves pesticide spraying efficiency by controlling droplet size, density, and distribution.

6.1. Vehicle Automatic Control Technology

With minimal human intervention, vehicle automatic control technology uses advanced sensors, decision making, and control systems to enable various vehicles to autonomously complete tasks such as navigation, positioning, and autonomous driving. Among them, navigation and positioning technology mainly relies on GNSS, including the Global Positioning System (GPS) of the United States [190], China’s BeiDou Navigation Satellite System (BDS), Russia’s Global Navigation Satellite System (GLONASS) [191], and the European Union’s Galileo satellite navigation system (Galileo) [192]. Autonomous driving technologies, including driverless technologies, allow agricultural equipment to navigate and operate autonomously in the field. These technologies can provide precise geolocation information for agricultural machinery, allowing operating implements to follow predetermined paths and locations, reducing the need for manual operations and increasing the accuracy and efficiency of operations, thus enabling precise fertilizer, seeding, and pesticide spraying.

6.1.1. Accurate Positioning and Land Parcel Mapping

Navigation and positioning technology can provide precise geographic location information for every point within the farmland. High-precision positioning ensures that agricultural machinery can accurately reach the predetermined location, reducing the waste of pesticides and avoiding damage to non-target crops [193].

The precise mapping of plots is carried out using navigation and positioning technology to obtain precise boundaries, area, and topographic information and generate high-precision digital maps of the plots. These maps can be used to plan paths of pesticide spraying and ensure that the pesticide covers all areas to be treated [194].

6.1.2. Route Planning for Pesticide Application and Navigation Pesticide Spraying

Based on the mapping results, the spraying width of the application equipment, and the appropriate overlap, the optimal traveling path of the vehicle can be planned, and the design and management of the spraying strategy can be carried out by using GIS Pro 3.4 software in combination with GNSS data. This method not only adjusts the amounts of pesticides applied according to the specific conditions of the plot but also reduces the area of overlapped or missed spraying, thus improving the efficiency and accuracy of pesticide spraying [195,196]. A spraying vehicle equipped with navigation systems (e.g., UAVs, self-driving tractors, etc.) can spray pesticides precisely according to the designed application strategy, further ensuring accuracy and effectiveness [197,198].

6.1.3. Automated Driving and Obstacle Avoidance

The automated driving system uses navigation and positioning technology to ensure that the pesticide spraying equipment can automatically travel in the farmland according to the predetermined route. Combined with GIS-preset routes of pesticide spraying, the automated driving system can accurately control the farm machinery’s path to ensure that each crop receives the right amount of pesticide [199].

In addition, the pesticide spraying equipment is equipped with various sensors, such as radar, LiDAR, and cameras, which can monitor the surrounding environment in real time, automatically identify obstacles, and perform obstacle avoidance to ensure the safety of the pesticide application operation. Meanwhile, the system can also monitor the working status of the equipment and the amount of pesticide applied in real time to ensure the accuracy and reliability of the application operation.

6.2. Precise Spraying Technology

The technologies of variable-rate spraying, profiling spraying, targeting spraying, and anti-drift spraying all fall under the category of IPPS technology. All these technologies aim to optimize the use of pesticides or other agrochemicals by improving spraying precision, increasing crop yield, ensuring healthy plant growth, and reducing resource wastage and environmental pollution. The development timeline from hand sprayer to intelligent spraying technologies is shown in Figure 8.

6.2.1. Variable-Rate Spraying

Variable-rate spraying technology adapts spray volumes and strategies to suit different regions’ specific needs by monitoring target plant and soil conditions in real time [200,201]. This technology usually relies on advanced sensors, GNSS, and GIS systems to precisely control the spray volume to ensure that each area receives the optimal amount of pesticides it needs.

6.2.2. Profiling Spraying

Profiling spraying is a technology that automatically adjusts the height of the spray boom in response to changes in plant height or terrain to maintain an optimal distance between the spraying nozzle and the target plant or ground [202,203]. This ensures uniform spray coverage and reduces pesticide drift, increasing spraying efficiency and reducing environmental impact.

6.2.3. Targeting Spraying

Targeting technology focuses on accurately identifying crops and weeds and spraying only the plants that need to be treated [204,205]. This technique usually combines image recognition and AI algorithms and can significantly reduce the pesticides used while protecting the crop from non-targeted spraying.

6.2.4. Anti-Drift Spraying

Anti-drift spraying reduces drift during spraying by improving the nozzle design of droplet drift control, adjusting droplet size, and optimizing spray parameters. This technology ensures the sprayed pesticide reaches the target area more accurately, reducing the impact on the surrounding environment and non-target crops [206,207,208,209].

The effectiveness of different intelligent spraying technology is shown in Table 3.

6.3. Droplet Characteristic Control Technology

The control technology of droplet characteristics is of great significance for improving the application efficiency of agricultural chemical pesticides, reducing environmental pollution, and protecting plant health. Droplet size, density, and distribution directly affect pesticides’ coverage, penetration capacity, and evaporation loss. Therefore, precise control of droplet characteristics can significantly improve the quality and efficiency of agricultural production.

6.3.1. Key Elements of Droplet Characteristic Control Technology

Droplet diameter is a key factor in deposition rate and coverage. Smaller droplets can improve coverage but are also more susceptible to drifting due to wind, increasing the potential risk to the surrounding environment. Therefore, choosing the right droplet size ensures the effectiveness of spraying and reduces the environmental impact [213,214,215,216].

Droplet deposition density refers to the number of droplets per unit area, directly affecting the pesticide’s uniform distribution and action effect. Appropriate deposition density helps to ensure the effective concentration of pesticides on the foliage of crops and avoid wastage or harm of the pesticide.

Droplet distribution uniformity refers to the concentration or dispersion of droplet distribution, which can be expressed by the relative spectral width, diffusion ratio, and coefficient of variation. Uniform droplet distribution can ensure that each crop can obtain enough pesticide coverage to improve the control effect.

The skewness of the droplet distribution describes the symmetry of the droplet size distribution, and the droplet distribution’s kurtosis describes the droplet distribution’s sharpness and the tail’s thickness [217]. The performance of the pesticide spraying system and the spraying effect can be assessed by analyzing the kurtosis and skewness of the droplet distribution. For example, a droplet size distribution close to normal (low kurtosis and skewness close to zero) may be desirable for applications requiring uniform droplet coverage.

6.3.2. Traditional Droplet Control Technology

Droplet size and spray pattern can be adjusted by improving the design of the nozzle, for example, by using different nozzle shapes, sizes, and materials. Adjusting the operating pressure of the spray equipment can also change the droplet size and spray rate. Specific surfactants or other additives can change the surface tension of the liquid, which affects droplet formation and size.

Hydrodynamic atomization is squeezing a liquid under high pressure through one or more small orifices (nozzles) to form droplets. The droplet diameter can be adjusted by varying parameters such as nozzle size, supply pressure, and the nature of the liquid. In particular, the pressure of the liquid as it passes through the nozzle can be varied by adjusting the pump’s output pressure or by using a pressure regulating valve [218]. Usually, the higher the liquid pressure, the smaller the generated droplets [205]. The hydraulic atomization nozzle is simple in structure [219], easy to use, and inexpensive, and it is widely used for pesticide spraying. However, hydrodynamic atomization has certain requirements on the viscosity and other physical properties of the liquid, and the obtained droplet size distribution range is wide [220], which may not meet the requirements of fine spraying to dynamically adjust the droplet diameter.

6.3.3. Smart Droplet Control Technology

1. Piezoelectric ultrasonic atomization uses the inverse piezoelectric effect of a piezoelectric ceramic to generate mechanical vibrations under the action of an electric field [221]. When vibration frequency becomes excessive, it is transmitted to the liquid in contact with it, and the liquid is atomized into tiny droplets via the cavitation effect [222] or the surface wave effect [223]. Figure 9 shows a schematic diagram of an ultrasonic atomizer consisting of a sandwich transducer and a variable amplitude rod. Adjusting the vibration frequency and power of the ultrasonic waves allows the droplet diameter to be dynamically and continuously regulated within a certain range. The higher the frequency, the smaller the droplets produced [224], and the higher the power, the higher the atomization efficiency [225]. Piezoelectric ultrasonic atomization can produce micron/sub-micron droplets [226]; for aqueous pesticides such as low-viscosity liquids, ultrasonic atomization produces droplets with particle sizes usually in the range of 1–100 μm, with narrow droplet size distributions, good uniformity, and relatively low energy consumption. However, the cost of piezoelectric ultrasonic atomization equipment is high, and the physical and chemical properties of the liquid have certain requirements; some solutions are not suitable for ultrasonic atomization. In addition, prolonged operation may lead to overheating of the piezoelectric ceramic, reducing the service life;

2. Gas-assisted atomization allows the liquid to meet the high-speed gas flow in the nozzle or atomization device and use the gas’s shear force, turbulence effect, or pressure difference to atomize the liquid into tiny droplets [227]. The breakup and refinement of the droplets during the atomization process can be controlled by adjusting parameters such as the gas flow rate and pressure [228] as well as the liquid flow rate and pressure [229], enabling the regulation of the droplet diameter. Higher gas flow rates or pressures usually produce smaller droplets [230];

3. Centrifugal atomizing nozzles utilize a rotating atomizing disk (or rotating wheel or rotating cage) to allow liquid delivered to the center of the high-speed rotating disk to be thrown outwards from the center by centrifugal force and form droplets as it leaves the edge [215]. Adjustment of the diameter of the droplets can be achieved by adjusting the rotational speed of the atomizing disk [231] and by replacing the atomizing disk [232] with different numbers of teeth. Taken together, centrifugal atomization can produce droplets in the range of a dozen microns to about a hundred microns, covering a fairly wide range of diameters, and it is difficult to reach the submicron level yet. The atomization of liquids using a rotating disk is easy to operate, does not require external pressure or gas flow, and can handle large quantities of liquids [233]. Therefore, centrifugal atomization is widely used in aerial pesticide applications [234]. However, the droplet size mainly depends on the rotational speed, resulting in a limited adjustment range of droplet diameter [235];

4. Electrostatic atomization is when a charged liquid in a high-voltage electrostatic field is subjected to a combination of surface tension, gravity, and electrostatic force, resulting in an extremely unstable droplet surface and splitting into droplets. The size and distribution of the droplets can be controlled by adjusting the voltage. Higher voltages typically produce smaller, more uniformly distributed droplets. Electrostatic atomization techniques can also be used to adjust the direction of flight and distribution range of the droplets by changing the layout of the electric field.

Combined navigation, positioning, automatic driving technologies, precision spraying technologies, and droplet characteristic control technologies represent the frontiers of modern precision agriculture. By providing precise location information, intelligent operation path planning, and efficient pesticide spraying strategies, these technologies greatly improve the efficiency and accuracy of agricultural production and reduce resource waste and environmental pollution. Precise plot mapping and path planning of pesticide spraying ensures comprehensive coverage of farmland management, while automated driving and obstacle avoidance technologies ensure operational safety and flexibility. Meanwhile, variable rate spraying technology and profile spraying technology for different plant needs and soil conditions further optimize the use of agricultural resources. Through modern droplet characteristic control technology, agricultural producers can apply pesticides more scientifically, significantly improving the quality and efficiency of agricultural production. With the continuous development of technology, these precision agriculture technologies will continue to promote the development of agriculture in the direction of high efficiency, intelligence, and environmental protection and make an important contribution to the sustainable development of global agriculture.

7. Research Prospects

With global climate change and the growing demand for agricultural production, pest, disease, and weed control faces enormous challenges. Traditional control methods can no longer meet modern agricultural production’s efficiency, environmental protection, and sustainable development needs. Therefore, developing key technologies for IPPS has become an important measure to solve this problem. IPPS systems can achieve early identification, precise positioning, and personalized control of pests, diseases, and weeds, which not only improves the control efficiency and effectiveness but also greatly reduces the use of pesticides and the impact on the environment. In addition, intelligent data analysis and decision support can provide scientific and reasonable prevention and control suggestions for agricultural production, further improving the intelligent level of agricultural production.

However, the implementation of IPPS technology faces significant challenges across multiple domains. Data collection and quality assurance have persistent issues with field data accuracy, reliability, and consistency, particularly when dealing with diverse environmental conditions and multi-source data integration. The information processing capabilities are currently limited by inadequate model generalization and inefficient real-time processing of diverse pest and disease data. Additionally, the system faces considerable challenges in prescription generation and decision support, including difficulties in developing personalized treatment plans and integrating multiple data sources for effective decision making. Implementation and control aspects also present significant hurdles, particularly in achieving precise variable flow spraying operations and maintaining consistent droplet characteristics during application.

In the future, with the continuous integration and application of advanced technologies such as AI, big data, IoT, remote sensing, etc., pest, disease, and weed control will usher in a revolutionary change. All kinds of target information acquisition technology, information processing technology, and implement and control technology in spraying technology for plant protection will be deeply integrated with intelligent agriculture and prescription agriculture, and a new IPPS system will be constructed by further overcoming the weak links at each technical level. In contrast, a new intelligent plant protection platform construction will be built with the rapid development of the internet and big data technology. Here, we put forward the development outlooks of the key technologies of IPPS for pest, disease, and weed control in the future from four perspectives:

1. At the target information acquisition layer, information acquisition systems should be studied based on the characteristics of pests, diseases, and weeds: research on a multiple information acquisition system that uses low-altitude UAVs carrying remote sensing platforms, image acquisition systems, acoustic wave sensors, and other fusion technologies to comprehensively collect information on plant victimization data; research on a system that can instantly detect the situation of plant infestation, real-time access to the growth status of plants at different times through target information acquisition technology, construction of agricultural big data, and comparing the growth characteristics of the target plants in the monitoring area with those of healthy plants to analyze the severity of the influence of pesticide damage; research on establishing the standardized data collection protocols and quality control systems; and research on developing the real-time data validation and error correction algorithms;

2. At the information processing layer, a multi-task recognition model of pests, diseases, and weeds is required as well as research on building a decision-making model for IPPS that can identify the positioning of pests, diseases, and weeds in a certain area at the same time; research on the integrated classification of the positioning model of pests, diseases, and weeds, training the model with the collected image data of diseases, pests, and weeds to improve its generalization ability and achieve multi-functionality to realize multifunctional identification tasks to reduce equipment expenditure and additional agricultural equipment operating time; research on generative AI for the generation of a large number of images and spectral data of pests, diseases, and weeds for continuous model improvement; and research on deploying efficient real-time processing algorithms with quality assurance mechanisms;

3. At the pesticide prescription spraying layer, a decision-support system should be built based on generative AI for the prescription of pests, diseases, and weeds: using ground-based IoT combined with UAVs and satellite remote sensing to achieve all-weather access to agricultural information; building a database of historical disaster information, historical weather, and environmental information, and pest, and weed, and pesticide types; uploading relative information to the global agricultural information sharing platform to promote global cooperation and localized strategy optimization; building a dynamic ecological model based on generative AI and a prescription generation system for IPPS by learning a large amount of pest, disease, and weed data and control methods; creating virtual models with generative AI to simulate the farmland environment and the development process of pests, diseases, and weeds in response to possible disaster situations for researchers or farmers to observe the control effects of different control strategies and the ecological impacts and to give personalized prescriptions for novel pesticide combinations; integrating multi-source data fusion from ground IoT, UAVs, and satellites; and enabling personalized prescription recommendations with uncertainty quantification;

4. At the implement and control layer, IPPS machinery should be developed: breaking through the existing crop canopy area based on the technical bottleneck of variable flow spraying operations as well as developing and profiling and targeting intelligent machinery that can achieve real-time variable flow, variable pressure for a different range, and variable spray direction based on plant varieties, densities, and types and locations of pests, diseases, and weeds under the condition of a constant droplet size.

In conclusion, the future development of IPPS technology for pest, disease, and weed control will be multidimensional and comprehensive. At the same time, policy support, interdisciplinary cooperation, and public awareness are also important factors in promoting the development of this technology, which will greatly promote the development of agricultural production in the direction of more efficient, environmentally friendly, and sustainable development and make an important contribution to global food security and ecological, environmental protection.

Institutional Review Board Statement

Not applicable.

Data Availability Statement

No new data were created.

Acknowledgments

We sincerely thank reviewers and editors for giving valuable revision comments for the manuscript improving.

Conflicts of Interest

The authors declare no conflicts of interest.

Footnotes

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Figures and Tables

Figure 1. Timeline of IPPS development.

Figure 2. Logical sequence diagram for IPPS technologies.

Figure 3. Key technologies in IPPS technologies.

Figure 4. Schematic of remote sensing.

Figure 5. Multispectral remote sensing images.

Figure 6. Classification of LiDAR.

Figure 7. Relationship between plant defense mechanisms and IPPS.

Figure 8. Development timeline of intelligent spraying technologies.

Figure 9. Ultrasonic atomization nozzle.

Table 1

The strengths and weaknesses of different target collection technologies.

	Strength	Weaknesses
Image-based	High-resolution, real-time processing capability, and relatively low-cost.	Weather-dependent, limited field of view, and requires good lighting conditions.
Remote sensing	Large area coverage, multiple spectral bands, and non-invasive.	High initial cost, affected by cloud cover, and lower spatial resolution for satellite-based systems.
Acoustic waves	Weather-independent, can detect internal damage, and works in low light.	Limited range, complex signal interpretation, and potential sensor damage risks.
Electronic nose	Early detection capability, non-destructive, and high-sensitivity.	Environmental interference, complex calibration requirements, and high maintenance needs.

Table 2

The strengths and weaknesses of different methods.

	Strengths	Weaknesses
Traditional methods	Well-established methods that are low-cost and easy toimplement.	Limited accuracy in complex scenarios; users need to have a rich experience.
DL methods	High accuracy, automatic featurelearning, and good generalization.	Requires large datasets; computationally intensive.
Molecular biology methods	High precision and early detectioncapability.	Time-consuming, expensive, requires specialized equipment and expertise, and can only applied in a controlled environment.

Table 3

The effectiveness of intelligent spraying technology.

Intelligent Spraying Technologies	Effectiveness	Ref.
The precision spraying system based on real-time sensors	Reduces pesticide use by 53.7 to 36.6%; reduces crop cost by 56.16%	[210]
Intelligent, variable-rate spray technology	Reduces total spray volume by 43%	[211]
Smart sprayer technology	Reduces pesticide application rates by 15% to 40% and non-target orchard-floor deposition by 5% to 72%	[212]

References

1. Wu, Z.; Wang, Z.; Spohrer, K. Non-contact leaf wetness measurement with laser-induced light reflection and RGB imaging. Biosyst. Eng.; 2024; 244, pp. 42-52. [DOI: https://dx.doi.org/10.1016/j.biosystemseng.2024.05.019]

2. Zheng, J.; Xu, Y. Development and Prospect in Environment-friendly Pesticide Sprayers. Trans. Chin. Soc. Agric. Mach.; 2021; 52, pp. 1-16.

3. Andrade, P.B.; Cruvinel, P.E.; Peñaloza, E. Module for Virtual Calibration of Sensors of Agricultural Spraying Systems (temperature, pressure and flow) Using an Arduino-based Architecture and a Controller Area Network Bus (CAN). Proceedings of the 12th IEEE International Conference on Semantic Computing (ICSC); Laguna Hills, CA, USA, 31 January–2 February 2018; pp. 352-357.

4. Liu, H.; Li, N.; Shen, Y.; Xu, H. Spray target detection based on laser scanning sensor and real-time correction of IMU attitude angle. Trans. Chin. Soc. Agric. Eng.; 2017; 33, pp. 88-97.

5. Yuan, L.; Pu, R.; Zhang, J.; Wang, J.; Yang, H. Using high spatial resolution satellite imagery for mapping powdery mildew at a regional scale. Precis. Agric.; 2016; 17, pp. 332-348. [DOI: https://dx.doi.org/10.1007/s11119-015-9421-x]

6. Librán-Embid, F.; Klaus, F.; Tscharntke, T.; Grass, I. Unmanned aerial vehicles for biodiversity-friendly agricultural landscapes—A systematic review. Sci. Total Environ.; 2020; 732, 139204. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2020.139204] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/32438190]

7. Albetis, J.; Duthoit, S.; Guttler, F.; Jacquin, A.; Goulard, M.; Poilvé, H.; Féret, J.B.; Dedieu, G. Detection of Flavescence dorée grapevine disease using unmanned aerial vehicle (UAV) multispectral imagery. Remote Sens.; 2017; 9, 308. [DOI: https://dx.doi.org/10.3390/rs9040308]

8. Lu, J.; Zhou, M.; Gao, Y.; Jiang, H. Using hyperspectral imaging to discriminate yellow leaf curl disease in tomato leaves. Precis. Agric.; 2018; 19, pp. 379-394. [DOI: https://dx.doi.org/10.1007/s11119-017-9524-7]

9. Hunter, J.E.; Gannon, T.W.; Richardson, R.J.; Yelverton, F.H.; Leon, R.G. Integration of remote-weed mapping and an autonomous spraying unmanned aerial vehicle for site-specific weed management. Pest Manag. Sci.; 2020; 76, pp. 1386-1392. [DOI: https://dx.doi.org/10.1002/ps.5651] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/31622004]

10. Maslekar, N.V.; Kulkarni, K.P.; Chakravarthy, A.K. Application of unmanned aerial vehicles (UAVs) for pest surveillance, monitoring and management. Innovative Pest Management Approaches for the 21st Century: Harnessing Automated Unmanned Technologies; Springer: Singapore, 2020; pp. 27-45.

11. Singh, V.; Bagavathiannan, M.; Chauhan, B.S.; Singh, S. Evaluation of current policies on the use of unmanned aerial vehicles in Indian agriculture. Curr. Sci.; 2019; 117, pp. 25-29. [DOI: https://dx.doi.org/10.18520/cs/v117/i1/25-29]

12. Restrepo-Arias, J.F.; Branch-Bedoya, J.W.; Awad, G. Image classification on smart agriculture platforms: Systematic literature review. Artif. Intell. Agric.; 2024; 13, pp. 1-17. [DOI: https://dx.doi.org/10.1016/j.aiia.2024.06.002]

13. Krestenitis, M.; Raptis, E.K.; Kapoutsis, A.C.; Ioannidis, K.; Kosmatopoulos, E.B.; Vrochidis, S. Overcome the Fear Of Missing Out: Active sensing UAV scanning for precision agriculture. Robot. Auton. Syst.; 2024; 172, 104581. [DOI: https://dx.doi.org/10.1016/j.robot.2023.104581]

14. Zhang, C.; Li, C.; He, M.; Cai, Z.; Feng, Z.; Qi, H.; Zhou, L. Leaf water content determination of oilseed rape using near-infrared hyperspectral imaging with deep learning regression methods. Infrared Phys. Technol.; 2023; 134, 104921. [DOI: https://dx.doi.org/10.1016/j.infrared.2023.104921]

15. Ahmad, M.N.; Shariff, A.; Moslim, R. Monitoring insect pest infestation via different spectroscopic techniques. Appl. Spectrosc. Rev.; 2018; 53, pp. 836-853. [DOI: https://dx.doi.org/10.1080/05704928.2018.1445094]

16. Yones, M.; Khdery, G.A.; Aboelghar, M.; Kadah, T.; Mamoun, S.A.M. Early detection of the Mediterranean Fruit Fly, Ceratitis capitata (Wied.) in oranges using different aspects of remote sensing applications. Egypt. J. Remote Sens. Space Sci.; 2023; 26, pp. 798-806. [DOI: https://dx.doi.org/10.1016/j.ejrs.2023.08.002]

17. Mei, L.; Guan, Z.G.; Zhou, H.J.; Lv, J.; Zhu, Z.R.; Cheng, J.A.; Chen, F.J.; Löfstedt, C.; Svanberg, S.; Somesfalean, G. Agricultural pest monitoring using fluorescence lidar techniques Feasibility study. Appl. Phys. B-Lasers Opt.; 2012; 106, pp. 733-740. [DOI: https://dx.doi.org/10.1007/s00340-011-4785-8]

18. Wang, A.; Zhang, W.; Wei, X. A review on weed detection using ground-based machine vision and image processing techniques. Comput. Electron. Agric.; 2019; 158, pp. 226-240. [DOI: https://dx.doi.org/10.1016/j.compag.2019.02.005]

19. Ye, H.; Lang, R.; Liu, C.; Li, M. Recognition of cucumber downy mildew disease based on visual saliency map. Trans. Chin. Soc. Agric. Mach.; 2016; 47, pp. 270-274.

20. Lian, Y.Y.; Wang, A.Q.; Zeng, B.; Yang, H.M.; Li, J.L.; Peng, S.H.; Zhou, S.H. Identification of male and female pupal characteristics of Zeugodacus cucurbitae (Coquillett) via machine vision. PLoS ONE; 2022; 17, e0264227. [DOI: https://dx.doi.org/10.1371/journal.pone.0264227] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/35324918]

21. Srinivas, L.; Bharathy, A.; Ramakuri, S.K.; Sethy, A.; Kumar, R. An optimized machine learning framework for crop disease detection. Multimed. Tools Appl.; 2023; 83, pp. 1539-1558. [DOI: https://dx.doi.org/10.1007/s11042-023-15446-2]

22. Zou, K.; Ge, L.; Zhou, H.; Zhang, C.; Li, W. Broccoli Seedling Pest Damage Degree Evaluation Based on Machine Learning Combined with Color and Shape Features. Inf. Process. Agric.; 2021; 8, pp. 505-514. [DOI: https://dx.doi.org/10.1016/j.inpa.2020.12.003]

23. Ali, H.; Lali, M.I.; Nawaz, M.Z.; Sharif, M.; Saleem, B.A. Symptom based automated detection of citrus diseases using color histogram and textural descriptors. Comput. Electron. Agric.; 2017; 138, pp. 92-104. [DOI: https://dx.doi.org/10.1016/j.compag.2017.04.008]

24. Zheng, Q.; Huang, W.J.; Xia, Q.; Dong, Y.Y.; Ye, H.C.; Jiang, H.; Chen, S.S.; Huang, S.Y. Remote Sensing Monitoring of Rice Diseases and Pests from Different Data Sources: A Review. Agronomy; 2023; 13, 1851. [DOI: https://dx.doi.org/10.3390/agronomy13071851]

25. Abd El-Ghany, N.M.; Abd El-Aziz, S.E.; Marei, S.S. A review: Application of remote sensing as a promising strategy for insect pests and diseases management. Environ. Sci. Pollut. Res.; 2020; 27, pp. 33503-33515. [DOI: https://dx.doi.org/10.1007/s11356-020-09517-2]

26. Zhang, J.C.; Huang, Y.B.; Pu, R.L.; Gonzalez-Moreno, P.; Yuan, L.; Wu, K.; Huang, W. Monitoring plant diseases and pests through remote sensing technology: A review. Comput. Electron. Agric.; 2019; 165, 104943. [DOI: https://dx.doi.org/10.1016/j.compag.2019.104943]

27. Yang, C. Remote sensing and precision agriculture technologies for crop disease detection and management with a practical application example. Engineering; 2020; 6, pp. 528-532. [DOI: https://dx.doi.org/10.1016/j.eng.2019.10.015]

28. Jorgensen, L.N.; Kudsk, P.; Orum, J.E. Links between pesticide use pattern and crop production in Denmark with special reference to winter wheat. Crop Prot.; 2019; 119, pp. 147-157. [DOI: https://dx.doi.org/10.1016/j.cropro.2019.01.024]

29. Maino, J.L.; Thia, J.; Hoffmann, A.A.; Umina, P.A. Estimating rates of pesticide usage from trends in herbicide, insecticide, and fungicide product registrations. Crop Prot.; 2023; 163, 106125. [DOI: https://dx.doi.org/10.1016/j.cropro.2022.106125]

30. Jordan, D.L.; Buol, G.S.; Brandenburg, R.L.; Shew, B.B.; Wilkerson, G.G.; Lassiter, B.R.; Dunne, J.; Gorny, A.; Washburn, D.; Hoisington, D. et al. A Risk Tool and Production Log Created using Microsoft Excel to Manage Pests in Peanut (Arachis hypogaea). J. Integr. Pest Manag.; 2022; 13, 9. [DOI: https://dx.doi.org/10.1093/jipm/pmac006]

31. Ren, S.; Chen, H.; Hou, J.; Zhao, P.; Dong, Q.; Feng, H. Based on historical weather data to predict summer field-scale maize yield: Assimilation of remote sensing data to WOFOST model by ensemble Kalman filter algorithm. Comput. Electron. Agric.; 2024; 219, 108822. [DOI: https://dx.doi.org/10.1016/j.compag.2024.108822]

32. Xiao, D.; Pan, Y.; Feng, J.; Yin, J.; Liu, Y.; He, L. Remote sensing detection algorithm for apple fire blight based on UAV multispectral image. Comput. Electron. Agric.; 2022; 199, 107137. [DOI: https://dx.doi.org/10.1016/j.compag.2022.107137]

33. Taiwo, B.E.; Kafy, A.A.; Samuel, A.A.; Rahaman, Z.A.; Ayowole, O.E.; Shahrier, M.; Duti, B.M.; Rahman, M.T.; Peter, O.T.; Abosede, O.O. Monitoring and predicting the influences of land use/land cover change on cropland characteristics and drought severity using remote sensing techniques. Environ. Sustain. Indic.; 2023; 18, 100248. [DOI: https://dx.doi.org/10.1016/j.indic.2023.100248]

34. Jiang, X.; Zhen, J.; Miao, J.; Zhao, D.; Shen, Z.; Jiang, J.; Gao, C.; Wu, G.; Wang, J. Newly-developed three-band hyperspectral vegetation index for estimating leaf relative chlorophyll content of mangrove under different severities of pest and disease. Ecol. Indic.; 2022; 140, 108978. [DOI: https://dx.doi.org/10.1016/j.ecolind.2022.108978]

35. Lassalle, G. Monitoring natural and anthropogenic plant stressors by hyperspectral remote sensing: Recommendations and guidelines based on a meta-review. Sci. Total Environ.; 2021; 788, 147758. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2021.147758]

36. Neinavaz, E.; Schlerf, M.; Darvishzadeh, R.; Gerhards, M.; Skidmore, A.K. Thermal infrared remote sensing of vegetation: Current status and perspectives. Int. J. Appl. Earth Obs. Geoinf.; 2021; 102, 102415. [DOI: https://dx.doi.org/10.1016/j.jag.2021.102415]

37. Jones, H.G.; Serraj, R.; Loveys, B.R.; Xiong, L.Z.; Wheaton, A.; Price, A.H. Thermal infrared imaging of crop canopies for the remote diagnosis and quantification of plant responses to water stress in the field. Funct. Plant Biol.; 2009; 36, pp. 978-989. [DOI: https://dx.doi.org/10.1071/FP09123] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/32688709]

38. Zhou, X.; Chen, Z.; Wang, Z.; Sun, D.; Yang, L.; Yan, G.; Song, S. Effects of the soil moisture content and leaf memory effect on pesticide droplet absorption. Sci. Hortic.; 2024; 329, 113040. [DOI: https://dx.doi.org/10.1016/j.scienta.2024.113040]

39. Sinha, A.; Tan, W.K.; Li, Y.F.; McNairn, H.; Jiao, X.F.; Hosseini, M. Applying a particle filtering technique for canola crop growth stage estimation in Canada: Remote Sensing For Agriculture, Ecosystems, And Hydrology XIX. Proceedings of the Conference on Remote Sensing for Agriculture, Ecosystems, and Hydrology; Warsaw, Poland, 11–14 September 2017; Neale, C.; Maltese, A. 10421.

40. Hunt, D.A.; Tabor, K.; Hewson, J.H.; Wood, M.A.; Reymondin, L.; Koenig, K.; Schmitt-Harsh, M.; Follett, F. Review of Remote Sensing Methods to Map Coffee Production Systems. Remote Sens.; 2020; 12, 2041. [DOI: https://dx.doi.org/10.3390/rs12122041]

41. Zou, K.L.; Wang, H.; Zhang, F.; Zhang, C.L.; Kai, D. Precision route planning method based on UAV remote sensing and genetic algorithm for weeding machine. Appl. Intell.; 2023; 53, pp. 11203-11213. [DOI: https://dx.doi.org/10.1007/s10489-022-03965-8]

42. Zhang, R.R.; Lian, S.K.; Li, L.L.; Zhang, L.H.; Zhang, C.C.; Chen, L.P. Design and experiment of a binocular vision-based canopy volume extraction system for precision pesticide application by UAVs. Comput. Electron. Agric.; 2023; 213, 108197. [DOI: https://dx.doi.org/10.1016/j.compag.2023.108197]

43. Vanegas, F.; Bratanov, D.; Powell, K.; Weiss, J.; Gonzalez, F. A Novel Methodology for Improving Plant Pest Surveillance in Vineyards and Crops Using UAV-Based Hyperspectral and Spatial Data. Sensors; 2018; 18, 260. [DOI: https://dx.doi.org/10.3390/s18010260] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/29342101]

44. Srivastava, A.; Prakash, J. Techniques, Answers, and Real-World UAV Implementations for Precision Farming. Wirel. Pers. Commun.; 2023; 131, pp. 2715-2746. [DOI: https://dx.doi.org/10.1007/s11277-023-10577-z]

45. Gu, C.C.; Zhai, C.Y.; Wang, X.; Wang, S.L. CMPC: An Innovative Lidar-Based Method to Estimate Tree Canopy Meshing-Profile Volumes for Orchard Target-Oriented Spray. Sensors; 2021; 21, 4252. [DOI: https://dx.doi.org/10.3390/s21124252]

46. Liu, X.Y.; Wang, Y.X.; Kang, F.; Yue, Y.; Zheng, Y.J. Canopy Parameter Estimation of Citrus grandis var. Longanyou Based on LiDAR 3D Point Clouds. Remote Sens.; 2021; 13, 1859. [DOI: https://dx.doi.org/10.3390/rs13091859]

47. Mahmud, M.S.; Zahid, A.; He, L.; Choi, D.; Krawczyk, G.; Zhu, H.P. LiDAR-sensed tree canopy correction in uneven terrain conditions using a sensor fusion approach for precision sprayers. Comput. Electron. Agric.; 2021; 191, 106565. [DOI: https://dx.doi.org/10.1016/j.compag.2021.106565]

48. Li, Q.; Zheng, J.; Zhou, H.; Zhang, H.; Shu, Y.; Xu, B. Online Measurement of Tree Canopy Volume Using Vehicle-borne 2-D Laser Scanning. Trans. Chin. Soc. Agric. Mach.; 2016; 47, pp. 309-314.

49. Martin, B.; Juliet, V.; Sankaranarayanan, P.E.; Gopal, A.; Rajkumar, I. Wireless implementation of mems accelerometer to detect red palm weevil on palms. Proceedings of the International Conference on Advanced Electronic Systems; Pilani, India, 21–23 September 2013.

50. Mankin, R.W.; Smith, M.T.; Tropp, J.M.; Atkinson, E.B.; Jong, D.Y. Detection of Anoplophora glabripennis (Coleoptera: Cerambycidae) Larvae in Different Host Trees and Tissues by Automated Analyses of Sound-Impulse Frequency and Temporal Patterns. J. Econ. Entomol.; 2008; 101, pp. 838-849. [DOI: https://dx.doi.org/10.1603/0022-0493(2008)101[838:DOAGCC]2.0.CO;2]

51. Pinhas, J.; Soroker, V.; Hetzroni, A.; Mizrach, A.; Teicher, M.; Goldberger, J. Automatic acoustic detection of the red palm weevil. Comput. Electron. Agric.; 2008; 63, pp. 131-139. [DOI: https://dx.doi.org/10.1016/j.compag.2008.02.004]

52. Leblanc, M.; Gaunt, D.; Fleurat-Lessard, F. Experimental study of acoustic equipment for real-time insect detection in grain bins—Assessment of their potential for infestation risk prediction during long term storage periods. IOBC WPRS Bull.; 2011; 69, pp. 79-88.

53. Pearson, T.C.; Cetin, A.E.; Tewfik, A.H.; Haff, R.P. Feasibility of impact-acoustic emissions for detection of damaged wheat kernels. Digit. Signal Process.; 2007; 17, pp. 617-633. [DOI: https://dx.doi.org/10.1016/j.dsp.2005.08.002]

54. Kim, K.; Lee, J.; Lee, S.; Yeo, H. Improvement of wood CT images by consideration of the skewing of ultrasound caused by growth ring angle. Wood Fiber Sci.; 2008; 40, pp. 572-579.

55. Markom, M.A.; Shakaff, A.Y.M.; Adom, A.H.; Ahmad, M.N.; Hidayat, W.; Abdullah, A.H.; Fikri, N.A. Intelligent electronic nose system for basal stem rot disease detection. Comput. Electron. Agric.; 2009; 66, pp. 140-146. [DOI: https://dx.doi.org/10.1016/j.compag.2009.01.006]

56. Lampson, B.D.; Han, Y.J.; Khalilian, A.; Greene, J.K.; Degenhardt, D.C.; Hallstrom, J.O. Development of a portable electronic nose for detection of pests and plant damage. Comput. Electron. Agric.; 2014; 108, pp. 87-94. [DOI: https://dx.doi.org/10.1016/j.compag.2014.07.002]

57. Cui, S.Q.; Inocente, E.; Acosta, N.; Keener, H.M.; Zhu, H.P.; Ling, P.P. Development of Fast E-nose System for Early-Stage Diagnosis of Aphid-Stressed Tomato Plants. Sensors; 2019; 19, 3480. [DOI: https://dx.doi.org/10.3390/s19163480]

58. Brittany, D.L.; Ahmad, K.; Jeremy, K.G.; Young, J.H.; David, C.D. Development of a Portable Electronic Nose for Detection of Cotton Damaged by Nezara viridula (Hemiptera: Pentatomidae). J. Insects; 2014; 2014, pp. 1-8.

59. Wilson, A. Applications of Electronic-Nose Technologies for Noninvasive Early Detection of Plant, Animal and Human Diseases. Chemosensors; 2018; 6, 45. [DOI: https://dx.doi.org/10.3390/chemosensors6040045]

60. Zheng, Z.; Zhang, C. Electronic noses based on metal oxide semiconductor sensors for detecting crop diseases and insect pests. Comput. Electron. Agric.; 2022; 197, 106988. [DOI: https://dx.doi.org/10.1016/j.compag.2022.106988]

61. Alahmad, T.; Neményi, M.; Nyéki, A. Applying IoT Sensors and Big Data to Improve Precision Crop Production: A Review. Agronomy; 2023; 13, 2603. [DOI: https://dx.doi.org/10.3390/agronomy13102603]

62. Zou, X.G.; Liu, W.C.; Huo, Z.Q.; Wang, S.Y.; Chen, Z.L.; Xin, C.R.; Bai, Y.A.; Liang, Z.Y.; Gong, Y.; Qian, Y. et al. Current Status and Prospects of Research on Sensor Fault Diagnosis of Agricultural Internet of Things. Sensors; 2023; 23, 2528. [DOI: https://dx.doi.org/10.3390/s23052528]

63. Duguma, A.L.; Bai, X. Contribution of Internet of Things (IoT) in improving agricultural systems. Int. J. Environ. Sci. Technol.; 2024; 21, pp. 2195-2208. [DOI: https://dx.doi.org/10.1007/s13762-023-05162-7]

64. Tang, P.; Liang, Q.; Li, H.; Pang, Y.Y. Application of Internet-of-Things Wireless Communication Technology in Agricultural Irrigation Management: A Review. Sustainability; 2024; 16, 3575. [DOI: https://dx.doi.org/10.3390/su16093575]

65. Quy, V.K.; Hau, N.V.; Anh, D.V.; Quy, N.M.; Ban, N.T.; Lanza, S.; Randazzo, G.; Muzirafuti, A. IoT-Enabled Smart Agriculture: Architecture, Applications, and Challenges. Appl. Sci.; 2022; 12, 3396. [DOI: https://dx.doi.org/10.3390/app12073396]

66. Ojha, T.; Misra, S.; Raghuwanshi, N.S. Internet of Things for Agricultural Applications: The State of the Art. IEEE Internet Things J.; 2021; 8, pp. 10973-10997. [DOI: https://dx.doi.org/10.1109/JIOT.2021.3051418]

67. Li, X.M.; Hou, B.F.; Zhang, R.H.; Liu, Y.X. A Review of RGB Image-Based Internet of Things in Smart Agriculture. IEEE Sens. J.; 2023; 23, pp. 24107-24122. [DOI: https://dx.doi.org/10.1109/JSEN.2023.3309774]

68. Kalyani, Y.; Collier, R. A Systematic Survey on the Role of Cloud, Fog, and Edge Computing Combination in Smart Agriculture. Sensors; 2021; 21, 5922. [DOI: https://dx.doi.org/10.3390/s21175922]

69. Qureshi, T.; Saeed, M.; Ahsan, K.; Malik, A.A.; Muhammad, E.S.; Touheed, N. Smart Agriculture for Sustainable Food Security Using Internet of Things (IoT). Wirel. Commun. Mob. Comput.; 2022; 2022, 9608394. [DOI: https://dx.doi.org/10.1155/2022/9608394]

70. Wachowiak, M.P.; Walters, D.F.; Kovacs, J.M.; Wachowiak-Smolíková, R.; James, A.L. Visual analytics and remote sensing imagery to support community-based research for precision agriculture in emerging areas. Comput. Electron. Agric.; 2017; 143, pp. 149-164. [DOI: https://dx.doi.org/10.1016/j.compag.2017.09.035]

71. Shafi, U.; Mumtaz, R.; Iqbal, N.; Zaidi, S.M.H.; Zaidi, S.A.R.; Hussain, I.; Mahmood, Z. A Multi-Modal Approach for Crop Health Mapping Using Low Altitude Remote Sensing, Internet of Things (IoT) and Machine Learning. IEEE Access; 2020; 8, pp. 112708-112724. [DOI: https://dx.doi.org/10.1109/ACCESS.2020.3002948]

72. Zhang, H.; Wang, L.; Jin, X.; Bian, L.; Ge, Y. High-throughput phenotyping of plant leaf morphological, physiological, and biochemical traits on multiple scales using optical sensing. Crop J.; 2023; 11, pp. 1303-1318. [DOI: https://dx.doi.org/10.1016/j.cj.2023.04.014]

73. Shah, A.; Bangash, J.I.; Khan, A.W.; Ahmed, I.; Khan, A.; Khan, A.; Khan, A. Comparative analysis of median filter and its variants for removal of impulse noise from gray scale images. J. King Saud Univ.—Comput. Inf. Sci.; 2022; 34, pp. 505-519. [DOI: https://dx.doi.org/10.1016/j.jksuci.2020.03.007]

74. Hamuda, E.; Glavin, M.; Jones, E. A survey of image processing techniques for plant extraction and segmentation in the field. Comput. Electron. Agric.; 2016; 125, pp. 184-199. [DOI: https://dx.doi.org/10.1016/j.compag.2016.04.024]

75. Lu, C.; Arcega Rustia, D.J.; Lin, T. Generative Adversarial Network Based Image Augmentation for Insect Pest Classification Enhancement. IFAC-PapersOnLine; 2019; 52, pp. 1-5. [DOI: https://dx.doi.org/10.1016/j.ifacol.2019.12.406]

76. Zhang, J.; Wang, X.; Yang, C.; Zhang, J.; He, D.; Song, H. Image dehazing based on dark channel prior and brightness enhancement for agricultural remote sensing images from consumer-grade cameras. Comput. Electron. Agric.; 2018; 151, pp. 196-206. [DOI: https://dx.doi.org/10.1016/j.compag.2018.06.010]

77. Wu, J.; Xiang, L.; You, H.; Tang, L.; Gai, J. Plant-Denoising-Net (PDN): A plant point cloud denoising network based on density gradient field learning. ISPRS J. Photogramm. Remote Sens.; 2024; 210, pp. 282-299. [DOI: https://dx.doi.org/10.1016/j.isprsjprs.2024.03.010]

78. Luo, Z.; Yang, W.; Yuan, Y.; Gou, R.; Li, X. Semantic segmentation of agricultural images: A survey. Inf. Process. Agric.; 2024; 11, pp. 172-186. [DOI: https://dx.doi.org/10.1016/j.inpa.2023.02.001]

79. Cheng, J.; Deng, C.; Su, Y.; An, Z.; Wang, Q. Methods and datasets on semantic segmentation for Unmanned Aerial Vehicle remote sensing images: A review. ISPRS J. Photogramm. Remote Sens.; 2024; 211, pp. 1-34. [DOI: https://dx.doi.org/10.1016/j.isprsjprs.2024.03.012]

80. Raja, M.R.; Jayaraj, V.; Shajin, F.H.; Devi, E.M.R. Radial basis function Neural Network optimized with Salp Swarm algorithm espoused paddy leaf disease classification. Biomed. Signal Process. Control.; 2023; 86, 105038.

81. Zhao, S.L.; Sun, X.T.; Gai, L.Y. Data enhancement and multi-feature learning model for pest classification. J. Intell. Fuzzy Syst.; 2023; 45, pp. 5409-5421. [DOI: https://dx.doi.org/10.3233/JIFS-230606]

82. Nie, J.; Yuan, Y.C.; Li, Y.; Wang, H.T.; Li, J.B.; Wang, Y.; Song, K.L.; Ercisli, S. Few-shot Learning in Intelligent Agriculture: A Review of Methods and Applications. J. Agric. Sci.-Tarim Bilim. Derg.; 2024; 30, pp. 216-228. [DOI: https://dx.doi.org/10.15832/ankutbd.1339516]

83. Sulistyo, S.B.; Woo, W.L.; Dlay, S.S.; Gao, B. Building a Globally Optimized Computational Intelligent Image Processing Algorithm for On-Site Inference of Nitrogen in Plants. IEEE Intell. Syst.; 2018; 33, pp. 15-26. [DOI: https://dx.doi.org/10.1109/MIS.2018.111144506]

84. Lamparelli, R.; Mercante, E.; Rocha, J.V.; Opazo, M.A. Impact of the normalization process on the spectral-temporal profile of soybean crops based on vegetation indexes. Int. J. Remote Sens.; 2012; 33, pp. 1605-1626. [DOI: https://dx.doi.org/10.1080/01431161.2011.593582]

85. Wang, X.Y.; Shu, L.; Han, R.; Yang, F.; Gordon, T.; Wang, X.C.; Xu, H.Y. A Survey of Farmland Boundary Extraction Technology Based on Remote Sensing Images. Electronics; 2023; 12, 1156. [DOI: https://dx.doi.org/10.3390/electronics12051156]

86. Dhiman, P.; Kaur, A.; Balasaraswathi, V.R.; Gulzar, Y.; Alwan, A.A.; Hamid, Y. Image Acquisition, Preprocessing and Classification of Citrus Fruit Diseases: A Systematic Literature Review. Sustainability; 2023; 15, 9643. [DOI: https://dx.doi.org/10.3390/su15129643]

87. Wang, Z.B.; Cui, J.; Zhu, Y. Review of plant leaf recognition. Artif. Intell. Rev.; 2023; 56, pp. 4217-4253. [DOI: https://dx.doi.org/10.1007/s10462-022-10278-2]

88. Thenmozhi, K.; Reddy, U.S. Image Processing Techniques for Insect Shape Detection in Field Crops. Proceedings of the International Conference on Inventive Computing and Informatics (ICICI 2017); Coimbatore, India, 23–24 November 2017; IEEE: New York, NY, USA, pp. 699-704.

89. Nasreen, P.N.; Kumar, A.C.; Nabeel, P.A. Automatic Classification of Monocots and Dicots using SVM Classifier. Proceedings of the International Conference on Information Science (ICIS); Kochi, India, 12–13 August 2016; pp. 28-31.

90. Anton, C.A.; Matei, O.; Avram, A. Collaborative Data Mining in Agriculture for Prediction of Soil Moisture and Temperature. Software Engineering Methods in Intelligent Algorithms, Proceeding of the 8th Computer Science On-Line Conference (CSOC), Online, 24–27 April 2019; Silhavy, R. Springer: Cham, Switzerland, 2019; Volume 1, pp. 141-151.

91. Nie, J.; Wang, Y.; Li, Y.; Chao, X.W. Sustainable computing in smart agriculture: Survey and challenges. Turk. J. Agric. For.; 2022; 46, pp. 550-566. [DOI: https://dx.doi.org/10.55730/1300-011X.3025]

92. Song, L.M.; Liu, M.Y.; Liu, S.H.; Wang, H.Y.; Luo, J. Pest species identification algorithm based on improved YOLOv4 network. Signal Image Video Process.; 2023; 17, pp. 3127-3134. [DOI: https://dx.doi.org/10.1007/s11760-023-02534-x]

93. Dong, Z.G.; Li, L.; Wang, X.J.; Wang, G.C.; Gao, Y.; Wang, G.F. Tobacco pests monitoring system based on time sequence pattern mining. Proceedings of the IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS); Dalian, China, 20–22 March 2020; pp. 122-125.

94. Sharma, R.P.; Ramesh, D.; Pal, P.; Tripathi, S.; Kumar, C. IoT-Enabled IEEE 802.15.4 WSN Monitoring Infrastructure-Driven Fuzzy-Logic-Based Crop Pest Prediction. IEEE Internet Things J.; 2022; 9, pp. 3037-3045. [DOI: https://dx.doi.org/10.1109/JIOT.2021.3094198]

95. Worner, S.P.; Gevrey, M. Modelling global insect pest species assemblages to determine risk of invasion. J. Appl. Ecol.; 2006; 43, pp. 858-867. [DOI: https://dx.doi.org/10.1111/j.1365-2664.2006.01202.x]

96. Hong, Y.; Lee, M.; Rim, H.; Do, Y.; Kim, S.C.; Bang, J.H.; Song, U. Development of a preliminary environmental risk assessment system by using text mining for introducing alien crops. J. Environ. Manag.; 2022; 311, 114794. [DOI: https://dx.doi.org/10.1016/j.jenvman.2022.114794]

97. Hu, H.Y.; Su, C.; Yang, C.Y.; Yu, P. A Study on Intelligent Crop Disease and Pest Diagnosis System Based on Hadoop. Proceedings of the 2019 International Conference on Robots and Intelligent System (ICRIS); Haikou, China, 15–16 June 2019; pp. 171-173.

98. Iordache, M.D.; Mantas, V.; Baltazar, E.; Lewyckyj, N.; Souverijns, N. Application of Random Forest Classification to Detect the Pine Wilt Disease from High Resolution Spectral Images: IGARSS 2020. Proceedings of the 2020 IEEE International Geoscience and Remote Sensing Symposium (IGARSS); Waikoloa, HI, USA, 26 September–2 October 2020; pp. 4489-4492.

99. Zhang, L.B. Forecasting the Rice Stem Borer Occurrence Tendency based on Support Vector Machine. Proceedings of the 2009 ISECS International Colloquium on Computing, Communication, Control, and Management (CCCM 2009); Sanya, China, 8–9 August 2009; Luo, Q.; Yi, J.; Bin, C. Volume 3, pp. 356-359.

100. Yang, B.; Cao, W.Q.; Tian, C.M. Visual analysis of impact factors of forest pests and diseases. J. Vis.; 2019; 22, pp. 1257-1280. [DOI: https://dx.doi.org/10.1007/s12650-019-00593-2]

101. Verma, R.; Kushwaha, K.; Bijlwan, A.; Bisht, A.S. Enhancing urad bean (Vigna mungo L.) crop management with machine learning: Predictive analysis of pod rot severity and pod bug incidence patterns. Australas. Plant Pathol.; 2024; 53, pp. 273-283. [DOI: https://dx.doi.org/10.1007/s13313-024-00967-7]

102. Méndez-Vázquez, L.J.; Lasa-Covarrubias, R.; Cerdeira-Estrada, S.; Lira-Noriega, A. Using Simulated Pest Models and Biological Clustering Validation to Improve Zoning Methods in Site-Specific Pest Management. Appl. Sci.; 2022; 12, 1900. [DOI: https://dx.doi.org/10.3390/app12041900]

103. Zhang, Z.P.; Jeske, D.R.; Cui, X.P.; Hoddle, M. Co-clustering Spatial Data Using a Generalized Linear Mixed Model With Application to the Integrated Pest Management. J. Agric. Biol. Environ. Stat.; 2012; 17, pp. 265-282. [DOI: https://dx.doi.org/10.1007/s13253-012-0089-7]

104. Wang, W.Q.; Xiao, G.L.; Yang, B.Y.; Ye, J.; Zhang, X.; Zheng, Y.Q.; Chen, B. Instar Determination for the Tomato Leafminer Tuta absoluta (Lepidoptera: Gelechiidae) Using the Density-Based OPTICS Clustering Algorithm. Environ. Entomol.; 2022; 51, pp. 940-947. [DOI: https://dx.doi.org/10.1093/ee/nvac065] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/36066442]

105. Pratheepa, M.; Verghese, A.; Bheemanna, H. Weighted Association rule mining for the occurrence of the insect pest Helicoverpa armigera(Hubner) related with abiotic factors on cotton. Proceedings of the 3rd International Conference on Computing for Sustainable Global Development (INDIACom); New Delhi, India, 16–18 March 2016; Hoda, M.N. pp. 1884-1887.

106. Jin, X.; McCullough, P.E.; Liu, T.; Yang, D.; Zhu, W.; Chen, Y.; Yu, J. A smart sprayer for weed control in bermudagrass turf based on the herbicide weed control spectrum. Crop Prot.; 2023; 170, 106270. [DOI: https://dx.doi.org/10.1016/j.cropro.2023.106270]

107. Jin, X.; Liu, T.; Yang, Z.; Xie, J.; Bagavathiannan, M.; Hong, X.; Xu, Z.; Chen, X.; Yu, J.; Chen, Y. Precision weed control using a smart sprayer in dormant bermudagrass turf. Crop Prot.; 2023; 172, 106302. [DOI: https://dx.doi.org/10.1016/j.cropro.2023.106302]

108. Verma, T.; Dubey, S. Impact of Color Spaces and Feature Sets in Automated Plant Diseases Classifier: A Comprehensive Review Based on Rice Plant Images. Arch. Comput. Methods Eng.; 2020; 27, pp. 1611-1632. [DOI: https://dx.doi.org/10.1007/s11831-019-09364-6]

109. Wang, S.; Li, Y.; Yuan, J.; Song, L.; Liu, X.; Liu, X. Recognition of cotton growth period for precise spraying based on convolution neural network. Inf. Process. Agric.; 2021; 8, pp. 219-231. [DOI: https://dx.doi.org/10.1016/j.inpa.2020.05.001]

110. Tian, Y.N.; Wang, S.H.; Li, E.; Yang, G.D.; Liang, Z.Z.; Tan, M. MD-YOLO: Multi-scale Dense YOLO for small target pest detection. Comput. Electron. Agric.; 2023; 213, 108233. [DOI: https://dx.doi.org/10.1016/j.compag.2023.108233]

111. Bondre, S.; Patil, D. Recent advances in agricultural disease image recognition technologies: A review. Concurr. Comput-Pract. Exp.; 2023; 35, e7644. [DOI: https://dx.doi.org/10.1002/cpe.7644]

112. Zhong, Y.H.; Gao, J.Y.; Lei, Q.L.; Zhou, Y. A Vision-Based Counting and Recognition System for Flying Insects in Intelligent Agriculture. Sensors; 2018; 18, 1489. [DOI: https://dx.doi.org/10.3390/s18051489] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/29747429]

113. Liu, S.Q.; Jin, Y.S.; Ruan, Z.W.; Ma, Z.; Gao, R.; Su, Z.B. Real-Time Detection of Seedling Maize Weeds in Sustainable Agriculture. Sustainability; 2022; 14, 15088. [DOI: https://dx.doi.org/10.3390/su142215088]

114. Guo, B.L.; Ling, S.K.; Tan, H.Y.; Wang, S.; Wu, C.L.; Yang, D.S. Detection of the Grassland Weed Phlomoides umbrosa Using Multi-Source Imagery and an Improved YOLOv8 Network. Agronomy; 2023; 13, 3001. [DOI: https://dx.doi.org/10.3390/agronomy13123001]

115. Yu, Y.; Zhou, Q.; Wang, H.; Lv, K.; Zhang, L.J.; Li, J.; Li, D.M. LP-YOLO: A Lightweight Object Detection Network Regarding Insect Pests for Mobile Terminal Devices Based on Improved YOLOv8. Agriculture; 2024; 14, 1420. [DOI: https://dx.doi.org/10.3390/agriculture14081420]

116. Tang, Z.; Lu, J.J.; Chen, Z.Y.; Qi, F.; Zhang, L.Y. Improved Pest-YOLO: Real-time pest detection based on efficient channel attention mechanism and transformer encoder. Ecol. Inform.; 2023; 78, 102340. [DOI: https://dx.doi.org/10.1016/j.ecoinf.2023.102340]

117. Zhu, L.Q.; Li, X.M.; Sun, H.M.; Han, Y.P. Research on CBF-YOLO detection model for common soybean pests in complex environment. Comput. Electron. Agric.; 2024; 216, 108515. [DOI: https://dx.doi.org/10.1016/j.compag.2023.108515]

118. Xin, D.Y.; Li, T.Q. Revolutionizing tomato disease detection in complex environments. Front. Plant Sci.; 2024; 15, 1409544. [DOI: https://dx.doi.org/10.3389/fpls.2024.1409544]

119. Fang, J.X.; Jiang, H.T.; Zhang, S.Q.; Sun, L.; Hu, X.D.; Liu, J.; Gong, M.; Liu, H.X.; Fu, Y.Y. BAF-Net: Bidirectional attention fusion network via CNN and transformers for the pepper leaf segmentation. Front. Plant Sci.; 2023; 14, 1123410. [DOI: https://dx.doi.org/10.3389/fpls.2023.1123410]

120. Zhang, W.D.; Li, Z.X.; Li, G.H.; Zhuang, P.X.; Hou, G.J.; Zhang, Q.; Li, C.Y. GACNet: Generate Adversarial-Driven Cross-Aware Network for Hyperspectral Wheat Variety Identification. IEEE Trans. Geosci. Remote Sens.; 2024; 62, 5503314. [DOI: https://dx.doi.org/10.1109/TGRS.2023.3347745]

121. Zhang, W.D.; Li, Z.X.; Sun, H.H.; Zhang, Q.; Zhuang, P.X.; Li, C.Y. SSTNet: Spatial, Spectral, and Texture Aware Attention Network Using Hyperspectral Image for Corn Variety Identification. IEEE Geosci. Remote Sens. Lett.; 2022; 19, 5514205. [DOI: https://dx.doi.org/10.1109/LGRS.2022.3225215]

122. Bala, M.; Bansal, S. Review-Unveiling the Power of Deep Learning in Plant Pathology: A Review on Leaf Disease Detection. ECS J. Solid State Sci. Technol.; 2024; 13, 47003. [DOI: https://dx.doi.org/10.1149/2162-8777/ad3981]

123. Chore, A.; Thankachan, D. Nutrient Defect Detection In Plant Leaf Imaging Analysis Using Incremental Learning Approach with Multifrequency Visible Light Approach. J. Electr. Eng. Technol.; 2023; 18, pp. 1369-1387. [DOI: https://dx.doi.org/10.1007/s42835-022-01254-5]

124. Fu, M.X.; Lian, F.Y. Mildew Detection for Stored Wheat using Gas Chromatography-Ion Mobility Spectrometry and Broad Learning Network. Food Anal. Methods; 2024; 17, pp. 664-678. [DOI: https://dx.doi.org/10.1007/s12161-024-02600-1]

125. Saadati, M.; Toorchi, M. The study of plant protein accumulation in gut of insect using proteomics technique: Wheat–sunn pest interaction. J. Saudi Soc. Agric. Sci.; 2017; 16, pp. 205-209. [DOI: https://dx.doi.org/10.1016/j.jssas.2015.06.005]

126. Mendoza-Porras, O.; Nguyen, T.V.; Shah, R.M.; Thomas-Hall, P.; Bastin, L.; Deaker, D.J.; Motti, C.A.; Byrne, M.; Beale, D.J. Biochemical metabolomic profiling of the Crown-of-Thorns Starfish (Acanthaster): New insight into its biology for improved pest management. Sci. Total Environ.; 2023; 861, 160525. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2022.160525]

127. Wu, Z.; Liu, Z.; Hu, Z.; Wang, T.; Teng, L.; Dai, T.; Liu, P.; Hao, J.; Liu, X. Utilizing metabolomic approach to study the mode of action of fungicides and corresponding resistance in plant pathogens. Adv. Agrochem; 2024; 3, pp. 197-205. [DOI: https://dx.doi.org/10.1016/j.aac.2024.05.001]

128. Feng, Z.; Liu, N.; Tu, P.; Zou, Y.; Vosatka, M.; Zhao, Z.; Chen, J.; Song, H. Metabolomics Analysis of Bahia Grass (Paspalum notatum) Inoculated with Arbuscular Mycorrhizal Fungi exposed to soil Cd Stress. Environ. Exp. Bot.; 2024; 226, 105867. [DOI: https://dx.doi.org/10.1016/j.envexpbot.2024.105867]

129. Scheffler, B.E.; Michel, A.; Scheffler, J.A.; Duke, S.O. Molecular methods in weed science. Z. Pflanzenkrankh. Pflanzenschutz-J. Plant Dis. Prot.; 2002; 28, pp. 45-56.

130. Nayak, A.K.; Golive, P.; Sasmal, A.; Devanna, B.N.; Anilkumar, C.; Mukherjee, A.K.; Dash, S.S.; Das, M.S.; Subudhi, H. Exploring genetic divergence and marker-trait associations for leaffolder Cnaphalocrocis medinalis (Guenee) resistance in rice landraces. 3 Biotech; 2024; 14, 90. [DOI: https://dx.doi.org/10.1007/s13205-024-03930-x] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/38414829]

131. Su, S.; Zuo, Y.Y.; Zhang, X.H.; Jian, C.Z.; Peng, X.; Piñero, J.C.; Chen, M.H. Efficient CRISPR/Cas9-mediated white gene editing in the global tortricid fruit pest Grapholita molesta. Entomol. Gen.; 2022; 42, pp. 987-996. [DOI: https://dx.doi.org/10.1127/entomologia/2022/1563]

132. Yan, R.; Lin, X. CRISPR/Cas9-Mediated Genome Editing System in Insect Genomics and Pest Management. Methods in Molecular Biology; Humana: New York, NY, USA, 2022; 2360, pp. 347-366.

133. Chen, X.; Palli, S.R. Genome editing in pests: Basic science to applications. J. Pest Sci.; 2024; 97, pp. 1135-1152. [DOI: https://dx.doi.org/10.1007/s10340-023-01736-z]

134. Lujan, P.A. Management of Phytophthora Blight on Chile Pepper with Pecan Byproduct Extracts. Ph.D. Thesis; New Mexico State University: Las Cruces, NM, USA, 2022.

135. Ito, A.; Kamiya, J.; Katsuno, N.; Yanase, E. Alterations in Nonvolatile Components of Tea (Camellia sinensis) Induced by Insect Feeding under Field Conditions. Horticulturae; 2023; 9, 1078. [DOI: https://dx.doi.org/10.3390/horticulturae9101078]

136. Silva, F.L.; Quiroz-Carreño, S.; Ferreira, M.; Wei, Z.J.; Thakur, K.; Lv, X.G.; Avila-Acevedo, J.G.; Kubo, I.; Seigler, D.S.; Zengin, G. et al. Exploring the potential of Fabiana imbricata Ruiz et Pav. (“Pichi”) against pest insects and pathogenic microorganisms for crop protection. S. Afr. J. Bot.; 2022; 151, pp. 114-127. [DOI: https://dx.doi.org/10.1016/j.sajb.2021.11.053]

137. Sampathkumar, A.; Aiyanathan, K.; Nakkeeran, S.; Manickam, S. Multifaceted Bacillus spp. for the management of cotton bacterial blight caused by Xanthomonas citri pv. malvacearum. Biol. Control; 2023; 177, 105111. [DOI: https://dx.doi.org/10.1016/j.biocontrol.2022.105111]

138. Zhang, N.; Tan, W.W.; Luo, G.M.; Pu, T.M.; Wang, J.Q.; Zhang, X.H.; Song, Y.H. Untargeted Metabolite Profiling of Camellia tetracocca’s Response to an Empoasca onukii Attack Using GC-MS and LC-MS. Agronomy; 2023; 13, 791. [DOI: https://dx.doi.org/10.3390/agronomy13030791]

139. Argotte-Ramos, R.; Cime-Castillo, J.; Vargas, V.; Lanz-Mendoza, H.; Rodriguez, M.H.; Rodriguez, M.C. Development of an Enzyme-Linked Immunosorbent Assay (ELISA) as a tool to detect NS1 of dengue virus serotype 2 in female Aedes aegypti eggs for the surveillance of dengue fever transmission. Heliyon; 2024; 10, e29329. [DOI: https://dx.doi.org/10.1016/j.heliyon.2024.e29329]

140. Soubry, I.; Doan, T.; Chu, T.; Guo, X. A Systematic Review on the Integration of Remote Sensing and GIS to Forest and Grassland Ecosystem Health Attributes, Indicators, and Measures. Remote Sens.; 2021; 13, 3262. [DOI: https://dx.doi.org/10.3390/rs13163262]

141. Thomas, C.S.; Skinner, P.W.; Fox, A.D.; Greer, C.A.; Gubler, W.D. Utilization of GIS/GPS-based information technology in commercial crop decision making in California, Washington, Oregon, Idaho, and Arizona. J. Nematol.; 2002; 34, pp. 200-206. [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/19265934]

142. Di Guardo, A.; Capri, E.; Calliera, M.; Finizio, A. MIMERA: An online tool for the sustainable pesticide use at field scale. Sci. Total Environ.; 2022; 846, 157285. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2022.157285] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/35863569]

143. Kumari, P.; Mishra, G.C.; Srivastava, C.P. Forecasting models for predicting pod damage of pigeonpea in Varanasi region. J. Agrometeorol.; 2017; 19, pp. 265-269. [DOI: https://dx.doi.org/10.54386/jam.v19i3.669]

144. Damos, P. A stepwise algorithm to detect significant time lags in ecological time series in terms of autocorrelation functions and ARMA model optimisation of pest population seasonal outbreaks. Stoch. Environ. Res. Risk Assess.; 2016; 30, pp. 1961-1980. [DOI: https://dx.doi.org/10.1007/s00477-015-1150-1]

145. Chiu, L.; Rustia, D.J.A.; Lu, C.; Lin, T. Modelling and Forecasting of Greenhouse Whitefly Incidence Using Time-Series and ARIMAX Analysis. IFAC-PapersOnLine; 2019; 52, pp. 196-201. [DOI: https://dx.doi.org/10.1016/j.ifacol.2019.12.521]

146. Zubair, M.; Ahmed, S.; Dey, A.; Das, A.; Hasan, M.M. An Intelligent Model to Suggest Top Productive Seasonal Crops Based on User Location in the Context of Bangladesh. Smart Systems: Innovations in Computing (SSIC 2021), Proceedings of the 3rd International Conference on Smart Systems—Innovations in Computing (SSIC), Singapore, 22–23 January 2021; Somani, A.K.; Mundra, A.; Doss, R.; Bhattacharya, S. Springer: Singapore, 2022; Volume 235, pp. 289-300.

147. Wang, X.Y.; Kong, L.Y.; Zhi, P.F.; Chang, C. Update on Cuticular Wax Biosynthesis and Its Roles in Plant Disease Resistance. Int. J. Mol. Sci.; 2020; 21, 5514. [DOI: https://dx.doi.org/10.3390/ijms21155514] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/32752176]

148. Balakrishnan, D.; Bateman, N.; Kariyat, R.R. Rice physical defenses and their role against insect herbivores. Planta; 2024; 259, 110. [DOI: https://dx.doi.org/10.1007/s00425-024-04381-7] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/38565704]

149. Arya, G.C.; Sarkar, S.; Manasherova, E.; Aharoni, A.; Cohen, H. The Plant Cuticle: An Ancient Guardian Barrier Set Against Long-Standing Rivals. Front. Plant Sci.; 2021; 12, 663165. [DOI: https://dx.doi.org/10.3389/fpls.2021.663165]

150. Halpern, M.; Raats, D.; Lev-Yadun, S. Plant biological warfare: Thorns inject pathogenic bacteria into herbivores. Environ. Microbiol.; 2007; 9, pp. 584-592. [DOI: https://dx.doi.org/10.1111/j.1462-2920.2006.01174.x] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/17298359]

151. Kavitha, R.S.; Balamohan, T.N.; Kavitha, M.; Selvi, B.S. Biochemical interactions of banana hybrids to root lesion nematodes (Pratylenchus coffeae). Plant Arch.; 2008; 8, pp. 105-110.

152. Shafiei, F.; Shahidi-Noghabi, S.; Sedaghati, E.; Smagghe, G. Arbuscular Mycorrhizal Fungi Inducing Tomato Plant Resistance and Its Role in Control of Bemisia tabaci Under Greenhouse Conditions. Neotrop. Entomol.; 2024; 53, pp. 424-438. [DOI: https://dx.doi.org/10.1007/s13744-024-01135-8]

153. Stenberg, J.A.; Lehrman, A.; Björkman, C. Plant defence: Feeding your bodyguards can be counter-productive. Basic Appl. Ecol.; 2011; 12, pp. 629-633. [DOI: https://dx.doi.org/10.1016/j.baae.2011.08.007]

154. Van Oosten, V.R.; Bodenhausen, N.; Reymond, P.; Van Pelt, J.A.; Van Loon, L.C.; Dicke, M.; Pieterse, C. Differential effectiveness of microbially induced resistance against herbivorous insects in Arabidopsis. Mol. Plant-Microbe Interact.; 2008; 21, pp. 919-930. [DOI: https://dx.doi.org/10.1094/MPMI-21-7-0919]

155. N’Guessan, L.; Chillet, M.; Chiroleu, F.; Soler, A. Ecologically Based Management of Pineapple Mealybug Wilt: Controlling Dysmicoccus brevipes Mealybug Populations with Salicylic Acid Analogs and Plant Extracts. Horticulturae; 2024; 10, 227. [DOI: https://dx.doi.org/10.3390/horticulturae10030227]

156. Jeon, H.W.; Park, A.R.; Sung, M.; Kim, N.; Mannaa, M.; Han, G.; Kim, J.; Koo, Y.; Seo, Y.S.; Kim, J.C. Systemic Acquired Resistance-Mediated Control of Pine Wilt Disease by Foliar Application With Methyl Salicylate. Front. Plant Sci.; 2022; 12, 812414. [DOI: https://dx.doi.org/10.3389/fpls.2021.812414] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/35069670]

157. Bungala, L.; Park, C.; Dique, J.; Sathasivam, R.; Shin, S.Y.; Park, S.U. Ethylene: A Modulator of the Phytohormone-Mediated Insect Herbivory Network in Plants. Insects; 2024; 15, 404. [DOI: https://dx.doi.org/10.3390/insects15060404]

158. Li, A.M.; Wang, M.; Chen, Z.L.; Qin, C.X.; Liao, F.; Wu, Z.; He, W.Z.; Lakshmanan, P.; Pan, Y.Q.; Huang, D.L. Integrated Transcriptome and Metabolome Analysis to Identify Sugarcane Gene Defense against Fall Armyworm (Spodoptera frugiperda) Herbivory. Int. J. Mol. Sci.; 2022; 23, 13712. [DOI: https://dx.doi.org/10.3390/ijms232213712] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/36430189]

159. Lu, J.; Liu, J.; Chen, L.; Sun, J.; Su, Q.; Li, S.; Yang, J. Zhang, W. Screening of Brown Planthopper Resistant miRNAs in Rice and Their Roles in Regulation of Brown Planthopper Fecundity. Rice Sci.; 2022; 29, pp. 559-568.

160. Lv, L.J.; Guo, X.R.; Zhao, A.J.; Liu, Y.P.; Li, H.; Chen, X.Y. Combined analysis of metabolome and transcriptome of wheat kernels reveals constitutive defense mechanism against maize weevils. Front. Plant Sci.; 2023; 14, 1147145. [DOI: https://dx.doi.org/10.3389/fpls.2023.1147145]

161. Del Águila, I.M.; Cañadas, J.; Túnez, S. Decision making models embedded into a web-based tool for assessing pest infestation risk. Biosyst. Eng.; 2015; 133, pp. 102-115. [DOI: https://dx.doi.org/10.1016/j.biosystemseng.2015.03.006]

162. Pan, F.; Gao, L.J.; Zhu, K.H.; Du, G.L.; Zhu, M.M.; Zhao, L.; Gao, Y.L.; Tu, X.B.; Zhang, Z.H. Regional selection of insecticides and fungal biopesticides to control aphids and thrips and improve the forage quality of alfalfa crops. J. Integr. Agric.; 2023; 22, pp. 185-194. [DOI: https://dx.doi.org/10.1016/j.jia.2022.08.070]

163. Koppenhöfer, A.M.; Kostromytska, O.S.; Wu, S.H. Pyrethroid-Resistance Level Affects Performance of Larvicides and Adulticides From Different Insecticide Classes in Population of Listronotus maculicollis (Coleoptera: Curculionidae). J. Econ. Entomol.; 2018; 111, pp. 1851-1859. [DOI: https://dx.doi.org/10.1093/jee/toy142]

164. Kulye, M.; Mehlhorn, S.; Boaventura, D.; Godley, N. Venkatesh, SK.; Rudrappa, T.; Charan, T.; Rathi, D.; Nauen, R. Baseline Susceptibility of Spodoptera frugiperda Populations Collected in India towards Different Chemical Classes of Insecticides. Insects; 2021; 12, 758. [DOI: https://dx.doi.org/10.3390/insects12080758] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/34442324]

165. Stavrakaki, M.; Ilias, A.; Simoglou, K.B.; Mironidis, G.K.; Zimmer, C.T.; Souza, D.; Roditakis, E. Revision of Helicoverpa armigera insecticide resistance status in Greece. Crop Prot.; 2024; 175, 106446. [DOI: https://dx.doi.org/10.1016/j.cropro.2023.106446]

166. Muniz-Junior, G.; Roque, F.D.; Pires, A.P.; Guariento, R.D. Are lower pesticide doses better? An evolutionary perspective on integrated pest management. Ecol. Model.; 2023; 482, 110408. [DOI: https://dx.doi.org/10.1016/j.ecolmodel.2023.110408]

167. Gentil, C.; Basset-Mens, C.; Manteaux, S.; Mottes, C.; Maillard, E.; Biard, Y.; Fantke, P. Coupling pesticide emission and toxicity characterization models for LCA: Application to open-field tomato production in Martinique. J. Clean. Prod.; 2020; 277, 124099. [DOI: https://dx.doi.org/10.1016/j.jclepro.2020.124099]

168. Holbak, M.; Vuaille, J.; Diamantopoulos, E.; Styczen, M.E.; Petersen, C.T.; Strobel, B.W.; Abrahamsen, P. Application timing as a mitigation tool for pesticide leaching to drains in northwest Europe. J. Hydrol.-Reg. Stud.; 2024; 53, 101734. [DOI: https://dx.doi.org/10.1016/j.ejrh.2024.101734]

169. Quan, X.H.; Guo, Q.L.; Ma, J.; Doluschitz, R. The economic effects of unmanned aerial vehicles in pesticide application: Evidence from Chinese grain farmers. Precis. Agric.; 2023; 24, pp. 1965-1981. [DOI: https://dx.doi.org/10.1007/s11119-023-10025-9]

170. Gafni, R.; Ziv, G.A.; Eizenberg, H.; Blank, L. A regional-scale study of the contribution of local, management and climate factors to the infestation of processing tomato fields with Amaranthus species. Eur. J. Agron.; 2023; 143, 126722. [DOI: https://dx.doi.org/10.1016/j.eja.2022.126722]

171. Vuaille, J.; Holbak, M.; Perslev, M.; Diamantopoulos, E.; Jensen, S.M.; Styczen, M.E.; Petersen, C.T.; Strobel, B.W.; Abrahamsen, P. Can information on past and near-future weather and field conditions predict the safest pesticide application day?. Comput. Electron. Agric.; 2022; 203, 107454. [DOI: https://dx.doi.org/10.1016/j.compag.2022.107454]

172. Tudi, M.; Ruan, H.D.; Wang, L.; Lyu, J.; Sadler, R.; Connell, D.; Chu, C.; Phung, D.T. Agriculture Development, Pesticide Application and Its Impact on the Environment. Int. J. Environ. Res. Public Health; 2021; 18, 1112. [DOI: https://dx.doi.org/10.3390/ijerph18031112] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/33513796]

173. Rastgordani, F.; Oveisi, M.; Mashhadi, H.R.; Naeimi, M.H.; Hosseini, N.M.; Asadian, N.; Bakhshian, A.; Müller-Schärer, H. Climate change impact on herbicide efficacy: A model to predict herbicide dose in common bean under different moisture and temperature conditions. Crop Prot.; 2023; 163, 106097. [DOI: https://dx.doi.org/10.1016/j.cropro.2022.106097]

174. Yang, H.; Tan, Y.; Tang, S. From economic threshold to economic injury level: Modeling the residual effect and delayed response of pesticide application. Math. Biosci.; 2024; 373, 109223. [DOI: https://dx.doi.org/10.1016/j.mbs.2024.109223] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/38821257]

175. Yang, Y.Y.; Yang, M.; Zhao, T.; Pan, L.Y.; Jia, L.; Zheng, L.F. Residue and Risk Assessment of Fluopyram in Carrot Tissues. Molecules; 2022; 27, 5544. [DOI: https://dx.doi.org/10.3390/molecules27175544]

176. Zheng, Q.; Wu, J.; Yan, W.J.; Zhu, S.Q.; Miao, X.R.; Wang, R.F.; Huang, S.Q.; Cheng, D.M.; Zhang, P.W.; Zhang, Z.X. Green synthesis of a chlorfenapyr chitosan nanopesticide for maize root application: Reducing environmental pollution and risks to nontarget organisms. Int. J. Biol. Macromol.; 2023; 253, 126988. [DOI: https://dx.doi.org/10.1016/j.ijbiomac.2023.126988]

177. Wang, H.P.; Li, M.J.; Li, S.M.; Chen, X.Y.; Li, B.W.; Shao, H. Jin, F. Dissipation and potential risk of tristyrylphenol ethoxylate homologs in peanuts by spraying and root irrigation: A comparative assessment. J. Hazard. Mater.; 2024; 472, 134486. [DOI: https://dx.doi.org/10.1016/j.jhazmat.2024.134486] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/38714052]

178. Shang, Q.Q.; Lu, H.C.; Yang, M.D.; Wu, Y.J.; Chen, Q.; Yan, S. The Advancement and Prospects of the Tree Trunk Injection Technique in the Prevention and Control of Diseases and Pests. Agriculture; 2024; 14, 107. [DOI: https://dx.doi.org/10.3390/agriculture14010107]

179. Wheeler, C.E. Control of Pear Psylla in Pears and Black Stem Borer in Apples with Trunk Injection. Master’s Thesis; Michigan State University: East Lansing, MI, USA, 2020.

180. Archer, L.; Crane, J.H.; Albrecht, U. Trunk Injection as a Tool to Deliver Plant Protection Materials-An Overview of Basic Principles and Practical Considerations. Horticulturae; 2022; 8, 552. [DOI: https://dx.doi.org/10.3390/horticulturae8060552]

181. Ottis, B.V.; Mattice, J.D.; Talbert, R.E. Determination of antagonism between cyhalofop-butyl and other rice (Oryza sativa) herbicides in barnyardgrass (Echinochloa crus-galli). J. Agric. Food Chem.; 2005; 53, pp. 4064-4068. [DOI: https://dx.doi.org/10.1021/jf050006d]

182. Della Vechia, J.F.; Van Leeuwen, T.; Rossi, G.D.; Andrade, D.J. The role of detoxification enzymes in the susceptibility of Brevipalpus californicus exposed to acaricide and insecticide mixtures. Pestic. Biochem. Physiol.; 2021; 175, 104855. [DOI: https://dx.doi.org/10.1016/j.pestbp.2021.104855] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/33993973]

183. Han, L.; Wang, S.B.; Wang, Z.C.; Jin, L.J.; He, X.K. Method of 3D Voxel Prescription Map Construction in Digital Orchard Management Based on LiDAR-RTK Boarded on a UGV. Drones; 2023; 7, 242. [DOI: https://dx.doi.org/10.3390/drones7040242]

184. Li, X.J.; Liang, Z.; Yang, G.; Lin, T.; Liu, B. Assessing the Severity of Verticillium Wilt in Cotton Fields and Constructing Pesticide Application Prescription Maps Using Unmanned Aerial Vehicle (UAV) Multispectral Images. Drones; 2024; 8, 176. [DOI: https://dx.doi.org/10.3390/drones8050176]

185. Wang, Z.K.; Wen, S.; Lan, Y.B.; Liu, Y.; Dong, Y.Y. Variable-rate spray system for unmanned aerial applications using lag compensation algorithm and pulse width modulation spray technology. J. Agric. Eng.; 2024; 55, [DOI: https://dx.doi.org/10.4081/jae.2023.1547]

186. Yin, D.; Chen, S.; Pei, W.; Shen, B. Design of map-based indoor variable weed spraying system. Trans. Chin. Soc. Agric. Eng. (Trans. CSAE); 2011; 27, pp. 131-135.

187. Román, C.; Arnó, J.; Planas, S. Map-based zonal dosage strategy to control yellow spider mite (Eotetranychus carpini) and leafhoppers (Empoasca vitis & Jacobiasca lybica) in vineyards. Crop Prot.; 2021; 147, 105690.

188. Zhao, C.; Chen, T.; Chen, L.; Gao, Y. Decision-making support methods for precision pesticide application for preventing migratory pest disasters. Trans. Chin. Soc. Agric. Eng.; 2008; 24, (Suppl. S2), pp. 149-155.

189. Qiao, B.; He, X.; Wang, Z.; Han, L.; Liu, H.; Dong, X.; Liang, W. Development of variable-rate spraying system for high clearance wide boom sprayer based on LiDAR scanning. Trans. Chin. Soc. Agric. Eng.; 2020; pp. 89-95.

190. Rajak, P.; Roy, S.; Ganguly, A.; Mandi, M.; Dutta, A.; Das, K.; Nanda, S.; Ghanty, S. Biswas, G. Agricultural pesticides—Friends or foes to biosphere?. J. Hazard. Mater. Adv.; 2023; 10, 100264.

191. Xie, B.; Jin, Y.; Faheem, M.; Gao, W.; Liu, J.; Jiang, H.; Cai, L.; Li, Y. Research progress of autonomous navigation technology for multi-agricultural scenes. Comput. Electron. Agric.; 2023; 211, 107963. [DOI: https://dx.doi.org/10.1016/j.compag.2023.107963]

192. Wu, C.; Li, D.; Zhang, X.; Pan, J.; Quan, L.; Yang, L.; Yang, W.; Ma, Q. Su, C.; Zhai, W. China’s agricultural machinery operation big data system. Comput. Electron. Agric.; 2023; 205, 107594. [DOI: https://dx.doi.org/10.1016/j.compag.2022.107594]

193. Yao, Z.; Zhao, C.; Zhang, T. Agricultural machinery automatic navigation technology. iScience; 2024; 27, 108714. [DOI: https://dx.doi.org/10.1016/j.isci.2023.108714] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/38292432]

194. Yang, L.; Xu, Y.; Li, Y.; Chang, M.; Chen, Z.; Lan, Y.; Wu, C. Real-Time field road freespace extraction for agricultural machinery autonomous driving based on LiDAR. Comput. Electron. Agric.; 2023; 211, 108028. [DOI: https://dx.doi.org/10.1016/j.compag.2023.108028]

195. Huang, J.; Luo, Y.; Quan, Q.; Wang, B.; Xue, X.; Zhang, Y. An autonomous task assignment and decision-making method for coverage path planning of multiple pesticide spraying UAVs. Comput. Electron. Agric.; 2023; 212, 108128. [DOI: https://dx.doi.org/10.1016/j.compag.2023.108128]

196. Xu, J.; Liu, C.; Shao, J.; Xue, Y.; Li, Y. Collaborative orchard pesticide spraying routing problem with multi-vehicles supported multi-UAVs. J. Clean. Prod.; 2024; 458, 142429. [DOI: https://dx.doi.org/10.1016/j.jclepro.2024.142429]

197. Garg, S.; Rumjit, N.P.; Roy, S. Smart agriculture and nanotechnology: Technology, challenges, and new perspective. Adv. Agrochem; 2024; 3, pp. 115-125. [DOI: https://dx.doi.org/10.1016/j.aac.2023.11.001]

198. Fang, S.P.; Ru, Y.; Hu, C.M.; Yang, F.B. Planning of takeoff/landing site location, dispatch route, and spraying route for a pesticide application helicopter. Eur. J. Agron.; 2023; 146, 126814.

199. Wang, S.; Su, D.; Jiang, Y.; Tan, Y.; Qiao, Y.; Yang, S.; Feng, Y.; Hu, N. Fusing vegetation index and ridge segmentation for robust vision based autonomous navigation of agricultural robots in vegetable farms. Comput. Electron. Agric.; 2023; 213, 108235. [DOI: https://dx.doi.org/10.1016/j.compag.2023.108235]

200. Luo, S.; Wen, S.; Zhang, L.; Lan, Y.; Chen, X. Extraction of crop canopy features and decision-making for variable spraying based on unmanned aerial vehicle LiDAR data. Comput. Electron. Agric.; 2024; 224, 109197. [DOI: https://dx.doi.org/10.1016/j.compag.2024.109197]

201. Taseer, A.; Han, X. Advancements in variable rate spraying for precise spray requirements in precision agriculture using Unmanned aerial spraying Systems: A review. Comput. Electron. Agric.; 2024; 219, 108841. [DOI: https://dx.doi.org/10.1016/j.compag.2024.108841]

202. Pergher, G. Field evaluation of a calibration method for air-assisted sprayers involving the use of a vertical patternator. Crop Prot.; 2004; 23, pp. 437-446. [DOI: https://dx.doi.org/10.1016/j.cropro.2003.09.015]

203. Khot, L.R.; Ehsani, R.; Albrigo, G.; Landers, A.J.; Larbi, P.A. Technical Note: Spray Pattern Investigation of an Axial-Fan Airblast Precision Sprayer Using a Modified Vertical Patternator. Appl. Eng. Agric.; 2012; 28, pp. 647-654. [DOI: https://dx.doi.org/10.13031/2013.42426]

204. Fan, X.; Chai, X.; Zhou, J.; Sun, T. Deep learning based weed detection and target spraying robot system at seedling stage of cotton field. Comput. Electron. Agric.; 2023; 214, 108317. [DOI: https://dx.doi.org/10.1016/j.compag.2023.108317]

205. Brown, D.L.; Giles, D.K.; Oliver, M.N.; Klassen, P. Targeted spray technology to reduce pesticide in runoff from dormant orchards. Crop Prot.; 2008; 27, pp. 545-552. [DOI: https://dx.doi.org/10.1016/j.cropro.2007.08.012]

206. Djouhri, M.; Loubet, B.; Bedos, C.; Dages, C.; Douzals, J.P.; Voltz, M. ADDI-Spraydrift: A comprehensive model of pesticide spray drift with an assessment in vineyards. Biosyst. Eng.; 2023; 231, pp. 57-77. [DOI: https://dx.doi.org/10.1016/j.biosystemseng.2023.05.008]

207. Xue, S.; Han, J.; Xi, X.; Lan, Z.; Wen, R.; Ma, X. Coordination of distinctive pesticide adjuvants and atomization nozzles on droplet spectrum evolution for spatial drift reduction. Chin. J. Chem. Eng.; 2024; 66, pp. 250-262. [DOI: https://dx.doi.org/10.1016/j.cjche.2023.10.001]

208. Xue, S.; Xi, X.; Lan, Z.; Wen, R.; Ma, X. Longitudinal drift behaviors and spatial transport efficiency for spraying pesticide droplets. Int. J. Heat Mass Transf.; 2021; 177, 121516. [DOI: https://dx.doi.org/10.1016/j.ijheatmasstransfer.2021.121516]

209. Palleja, T.; Tresanchez, M.; Llorens, J.; Saiz-Vela, A. Design and characterization of a real-time capacitive system to estimate pesticides spray deposition and drift. Comput. Electron. Agric.; 2023; 207, 107720. [DOI: https://dx.doi.org/10.1016/j.compag.2023.107720]

210. Zanin AR, A.; Neves, D.C.; Teodoro, L.P.R.; da Silva, C.A.; da Silva, S.P.; Teodoro, P.E.; Baio, F.H.R. Reduction of pesticide application via real-time precision spraying. Sci. Rep.; 2022; 12, 5638. [DOI: https://dx.doi.org/10.1038/s41598-022-09607-w] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/35379871]

211. Fessler, L.; Sun, X.; Wright, W.C.; Zhu, H.; Fulcher, A. Intelligent, Variable-rate Spray Technology Reduces Total Pesticide Output while Controlling Foliar Disease of Shumard Oak1. J. Environ. Hortic.; 2023; 41, pp. 109-120. [DOI: https://dx.doi.org/10.24266/0738-2898-41.3.109]

212. Giles, D.K.; Klassen, P.; Niederholzer, F.; Downey, D. “Smart” sprayer technology provides environmental and economic benefits in California orchards. Calif. Agric.; 2011; 65, pp. 85-89. [DOI: https://dx.doi.org/10.3733/ca.v065n02p85]

213. Ji, G.M.; Chen, H.Z.; Zhang, Y.P.; Xiang, J.; Wang, Y.L.; Wang, Z.G.; Zhu, D.F.; Zhang, Y.K. Leaf surface characteristics affect the deposition and distribution of droplets in rice (Oryza sativa L.). Sci. Rep.; 2021; 11, 17846. [DOI: https://dx.doi.org/10.1038/s41598-021-97061-5] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/34497313]

214. Shan, C.F.; Wang, G.B.; Wang, H.H.; Xie, Y.J.; Wang, H.Z.; Wang, S.L.; Chen, S.D.; Lan, Y.B. Effects of droplet size and spray volume parameters on droplet deposition of wheat herbicide application by using UAV. Int. J. Agric. Biol. Eng.; 2021; 14, pp. 74-81. [DOI: https://dx.doi.org/10.25165/j.ijabe.20211401.6129]

215. Zhou, Q.Q.; Xue, X.Y.; Qin, W.C.; Cai, C.; Zhou, L.F. Optimization and test for structural parameters of UAV spraying rotary cup atomizer. Int. J. Agric. Biol. Eng.; 2017; 10, pp. 78-86.

216. Prokop, M.; Veverka, K. Influence of droplet spectra on the efficiency of contact and systemic herbicides. Plant Soil Environ.; 2003; 49, pp. 75-80. [DOI: https://dx.doi.org/10.17221/4093-PSE]

217. Ugbeh-Johnson, J.; Carpenter, M.; Okeke, N.E.; Mai, N. Characterization of water droplets size distribution in aviation turbine fuel: Ultrasonic homogeniser vs high shear speed mixer. Fuel; 2023; 332, 125674. [DOI: https://dx.doi.org/10.1016/j.fuel.2022.125674]

218. Sun, H.J.; Luo, Y.K.; Ding, H.B.; Li, J.X.; Song, C.R.; Liu, X.X. Experimental investigation on atomization properties of impaction-pin nozzle using imaging method analysis. Exp. Therm. Fluid Sci.; 2021; 122, 110322. [DOI: https://dx.doi.org/10.1016/j.expthermflusci.2020.110322]

219. Liu, J.P.; Liu, X.F.; Zhu, X.Y.; Yuan, S.Q. Droplet characterisation of a complete fluidic sprinkler with different nozzle dimensions. Biosyst. Eng.; 2016; 148, pp. 90-100. [DOI: https://dx.doi.org/10.1016/j.biosystemseng.2016.05.008]

220. Wang, D.H.; Hui, S.E.; Zhuang, H.Y. Effect of Atomization Pressure on Flow Rate and Droplet Diameter of Small-Bore Atomizing Nozzle. Proceedings of the 2015 International Conference on Applied Mechanics, Mechatronics and Intelligent Systems (Ammis2015); Qin, S.; Li, X. World Scientific Publishing: Singapore, 2016; pp. 33-37.

221. Qi, A.; Yeo, L.Y.; Friend, J.R. Interfacial destabilization and atomization driven by surface acoustic waves. Phys. Fluids; 2008; 20, 74103. [DOI: https://dx.doi.org/10.1063/1.2953537]

222. Topp, M.N. Ultrasonic atomization-a photographic study of the mechanism of disintegration. J. Aerosol Sci.; 1973; 4, pp. 17-25. [DOI: https://dx.doi.org/10.1016/0021-8502(73)90113-4]

223. Yuan, S.; Zhang, Y.; Gao, Y. Faraday wave instability characteristics of a single droplet in ultrasonic atomization and the sub-droplet generation mechanism. Exp. Therm. Fluid Sci.; 2022; 134, 110618. [DOI: https://dx.doi.org/10.1016/j.expthermflusci.2022.110618]

224. Kudo, T.; Sekiguchi, K.; Sankoda, K.; Namiki, N.; Nii, S. Effect of ultrasonic frequency on size distributions of nanosized mist generated by ultrasonic atomization. Ultrason. Sonochem.; 2017; 37, pp. 16-22. [DOI: https://dx.doi.org/10.1016/j.ultsonch.2016.12.019]

225. Barreras, F.; Amaveda, H.; Lozano, A. Transient high-frequency ultrasonic water atomization. Exp. Fluids; 2002; 33, pp. 405-413. [DOI: https://dx.doi.org/10.1007/s00348-002-0456-1]

226. Ramisetty, K.A.; Pandit, A.B.; Gogate, P.R. Investigations into ultrasound induced atomization. Ultrason. Sonochem.; 2013; 20, pp. 254-264. [DOI: https://dx.doi.org/10.1016/j.ultsonch.2012.05.001] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/22672979]

227. Zhao, J.; Fu, L.X.; Ding, H.Y.; Bai, B.; Zhang, D.P.; Liu, J.; He, X. Numerical simulation of working process and gas-liquid interaction mechanism of air assisted nozzle. Int. J. Multiph. Flow; 2023; 164, 104453. [DOI: https://dx.doi.org/10.1016/j.ijmultiphaseflow.2023.104453]

228. Du, B.X.; Zhao, Z.F. Numerical prediction of the spray from an air-assisted fuel injection system via Eulerian-Lagrangian approach. Energy Rep.; 2021; 7, pp. 6718-6732. [DOI: https://dx.doi.org/10.1016/j.egyr.2021.09.128]

229. Levitsky, I.; Tavor, D. Improved Atomization via a Mechanical Atomizer with Optimal Geometric Parameters and an Air-Assisted Component. Micromachines; 2020; 11, 584. [DOI: https://dx.doi.org/10.3390/mi11060584]

230. Avulapati, M.M.; Ravikrishna, R.V. Experimental Studies On Air-Assisted Atomization Of Jatropha Pure Plant Oil. At. Sprays; 2015; 25, pp. 553-569. [DOI: https://dx.doi.org/10.1615/AtomizSpr.2014010413]

231. Yang, Z.; Yu, J.X.; Duan, J.L.; Xu, X.; Huang, G.S. Optimization-Design and Atomization-Performance Study of Aerial Dual-Atomization Centrifugal Atomizer. Agriculture; 2023; 13, 430. [DOI: https://dx.doi.org/10.3390/agriculture13020430]

232. Liu, D.J.; Gong, Y.; Chen, X.; Zhang, X.; Wang, G. Design and experiment on atomizer parameter of impinging low-speed centrifugal atomization sprayer. Int. J. Agric. Biol. Eng.; 2020; 13, pp. 118-124. [DOI: https://dx.doi.org/10.25165/j.ijabe.20201306.5617]

233. Ru, Y.; Liu, Y.Y.; Qu, R.J.; Patel, M.K. Experimental study on spraying performance of biological pesticides in aerial rotary cage nozzle. Int. J. Agric. Biol. Eng.; 2020; 13, pp. 1-6. [DOI: https://dx.doi.org/10.25165/j.ijabe.20201306.5511]

234. Gong, Y.; Chen, X.B.; Liu, Y.; Pei, L.; Zhang, J.C. Design and Test of Controlled Droplet Sprayer for Facility Agriculture. Recent Highlights in Advanced Materials, Proceeding of the 2nd International Congress on Advanced Materials (ICAM), Zhenjiang, China, 16–19 May 2013; Liu, S.; Yuan, X.H. Trans Tech Publications Ltd.: Zhenjiang, China, 2014; Volume 575–576, pp. 481-486.

235. Dunkley, J.J. 1—Advances in atomisation techniques for the formation of metal powders. Advances in Powder Metallurgy; Woodhead Publishing: Sawston, UK, 2013; pp. 3-18.