Artificial Intelligence in Agricultural Mapping: A Review

Abstract

Artificial intelligence (AI) plays an essential role in agricultural mapping. It reduces costs and time and increases efficiency in agricultural management activities, which improves the food industry. Agricultural mapping is necessary for resource management and requires technologies for farming challenges. The mapping in agricultural AI applications gives efficiency in mapping and its subsequent use in decision-making. This study analyses AI’s current state in agricultural mapping through bibliometric indicators and a literature review to identify methods, agricultural resources, geomatic tools, mapping types, and their applications in agricultural management. The methodology begins with a bibliographic search in Scopus and the Web of Science (WoS). Subsequently, a bibliographic data analysis and literature review establish the scientific contribution, collaboration, AI methods, and trends. The United States (USA), Spain, and Italy are countries that produce and collaborate more in this area of knowledge. Of the studies, 76% use machine learning (ML) and 24% use deep learning (DL) for agricultural mapping applications. Prevailing algorithms such as Random Forest (RF), Artificial Neural Networks (ANNs), and Support Vector Machines (SVMs) correlate mapping activities in agricultural management. In addition, AI contributes to agricultural mapping in activities associated with production, disease detection, crop classification, rural planning, forest dynamics, and irrigation system improvements.

1. Introduction

Agriculture is the primary source of food and income and the backbone of some countries’ economies. It also provides raw materials for other industries’ production, contributing to their economies’ growth [1]. However, agricultural activities face problems such as climate change and decreased resources (e.g., water) that affect food security [2]. These challenges suggest the importance of agricultural land sustainable management, which requires spatial information on soil, water, and crops [3]. This management involves controlling, monitoring, and evaluating agricultural systems through supporting technologies such as artificial intelligence (AI) to solve farming problems.

AI is a strategy for optimising, automating, and managing large data volumes and various challenges, incorporating technological change [4]. It allows for the representation of complex data maps, the performance of mathematical models, and the improvement of traditional algorithm efficiency [5]. Cartography is a primary part of Geographic Information Systems (GISs) and territorial observation/management that explains natural and artificial environments based on spatial analysis [6,7]. Different mapping applications in various sciences widely use AI through different types of learning, such as deep learning (DL), machine learning (ML), and AI methods, such as Artificial Neural Network (ANN) models. For example:

• The application of AI with multimodal images and biopsy data to produce prostate cancer maps and estimation margins [8].

• Wetland mapping for spatial planning, environmental management, and biodiversity conservation [9].

• IP address mapping for cyberattack prevention [10].

• Spatial earthquake probability mapping based on ML and ANNs [11].

• Area estimation mapping with fog concentrations in hydrographic basins for integrated water resource management [12].

Furthermore, AI is an emerging technology in agriculture. Its applications stand out in crop yields, intelligent fumigation, agricultural robots, soil and crop monitoring [13], food security problems, climate uncertainty, and population growth [14]. The advancement of this technology has significantly changed agriculture because it provides various intelligent systems that monitor, control, and visualise agricultural activities in real time [15]. ML and DL are types of AI that use algorithms to estimate results with greater precision without human intervention [16,17]. These technologies have enabled controlled irrigation, pesticide use, and environmental pollution control through innovative agricultural practices [18]. Also, an ANN is an AI method used to detect, classify, and map crop diseases through images of a crop’s leaves [19].

Agricultural mapping provides specialised and accurate crop information for decision-makers, agrarian management, policy formulation and food security [20]. In addition, it contributes to thematic maps that constitute inputs for cropping systems and agricultural yield estimation [21]. These thematic maps involve strategies in agricultural activities such as soil properties’ spatial pattern characterisation [22], the distribution of plots by land use and land cover (LULC) [23], vegetation and crop detection [24], the spatial and temporal exploration of climate change effects in agricultural production [25], and areas suitable for crops’ biophysical-sociotechnical mapping [26]. However, some field activities, such as plant monitoring and phenotyping, require reducing human intervention with greater precision, giving way to essential technologies such as robotics and AI [17].

Various studies have been associated with the application of AI in agricultural mapping. For example, ref. [27] designed a small-scale agricultural robot prototype that identifies crop plots and can map and inspect a farming area. The robot’s decision-making relies on AI algorithms, which allow it to perform specific actions depending on the environment. In Brumadinho (Brazil), they mapped a flood distribution that invaded rivers and agricultural fields using remote sensing (RS), satellite images, and AI methods/algorithms such as ANNs and Support Vector Machines (SVMs). This study obtained a damage map to mitigate future flooding problems [28]. Furthermore, in the states of Goiás and Minas Gerais (Brazil), they mapped pivot irrigation systems using a very high-resolution image segmentation Convolutional Neural Network (CNN) to improve freshwater use monitoring in agricultural activities [29].

In Zhongning County, China, they conducted digital soil nutrient distribution mapping based on geo-plot boundaries. They used high-resolution images and ML algorithms to define the relationship between phosphorus and the environment. This study attempts to improve agriculture’s sustainability and solve the soil’s environmental contamination in this region [30]. In North Dakota (the United States), ref. [31] made seasonal crop maps using Deep Neural Network (DNN) and Landsat images with historical crop maps and soil measurements for training. This study obtained consistent DNN maps with less noise, reliability and accuracy.

Additionally, a researcher highlighted using this technology to identify extensive agricultural lands instead of scattered wetlands and suburban areas. In the Queensland region (Australia), they mapped agricultural drought risks through ML algorithms, such as Random Forests (RFs), SVMs, regression, and classification trees, using hydro-environmental data (e.g., water retention and precipitation) for soil moisture calculation. This study found very high drought-risk classes that require drought policies and environmental protection for the area [32]. In Calasparra (Spain) [33], they developed accurate crop mapping using a pixel-based supervised classification scheme, Sentinel-2 data, and ML algorithms for rice crop identification and abandoned plot detection.

These studies help us understand the challenges of using AI in agricultural mapping. The application and importance of AI in mapping provide several possibilities to transform data into meaningful information, respond to real-time situations, and optimise resource use, which contribute to decision-making. However, the fusion of AI methods with geomatic tools in agricultural mapping is necessary because they contribute to optimising agricultural production, increasing food production, improving territorial planning, and automating processes for food security. Therefore, a review of the scientific literature is necessary to identify, analyse, and further explore a better understanding of resources, AI methods, trend topics, and the basis for future research on AI applications in agricultural mapping. The bibliometric analysis and literature review explore the development of a particular field of knowledge, its vision of development in various regions, and the relationship between critical themes [34].

This study’s objective is to analyse the current state of AI in agricultural mapping through bibliometric indicators and a literature review of scientific publications in high-impact databases such as Scopus and the Web of Science (WoS), identifying methods, agricultural resources, geomatic tools, types of mapping, and their applications in agricultural management.

2. Materials and Methods

This study explores the structure and content of AI’s application in agricultural mapping. It also identifies scientific production, influential countries, their scientific collaboration, and trending topics. Figure 1 shows the study workflow using the methodological approach.

2.1. General Search

This phase builds a bibliometric database using the Scopus (Elsevier) and WoS (Clarivate) search engines. These databases have high-quality, multidisciplinary, standardised publications [35]. In this study, the search equation distinguishes terms related to the application of AI in agricultural mapping using Boolean operators for the association of terms: (“artificial intelligence”) AND (“agricultural mapping” OR “agricultural cartography”). The search found 944 documents distributed as 227 (Scopus) and 717 (WoS).

2.2. Bibliometrics

This phase merges the database documents into a single file (i.e., BibTex from Scopus and PlainText from WoS). Also, this phase eliminated duplicate records (76 documents) and records without an author (9), leaving 859 for data analysis. Bibliometric analyses measure current and future research trends, an authors’ impact, publications, and scientific collaboration in a field [36]. This study considered the scientific contributions based on the number of publications, the country contributions based on citation counts, collaboration analysis based on publication co-authorship, themes analysis, and trends through centrality measures (i.e., theme importance) and density (i.e., theme development) [37]. Finally, this phase eliminated non-English language records (91 documents) and unavailable records (12), leaving 756. The databases were processed and cleaned using the statistical program R-Studio (version R-4.1.2, Posit, Boston, MA, USA), Biblioshiny Web (version 4.1, K-Synth Srl, Academic Spin-Off of the University of Naples Federico II, Naples, Italy) and Microsoft Excel 365 (version 2405, Microsoft, Redmond, WA, USA) [38].

2.3. Review

Analysis units, such as titles and abstracts, contain a high density of appropriate words associated with each study’s research topic [39]. This study analysed these units in 756 publications. Of these, 550 documents focus on the environment, agricultural regulations, and coastline evolution, leaving a total of 206 records focused on the topic of this study. This review gathered detailed knowledge by extracting variables such as the country, resource, type of learning (methodology), thematic map, map use, resolution and geomatics tools [40] of the articles.

Additionally, this phase includes an analysis to validate/recognise the relationship contribution of AI in agricultural mapping using the Quality Function Deployment (QFD) methodology. This tool provides quality management/product design, construction, software development processes, higher education, industry, research and decision-making capabilities [41]. The qualitative analysis considered inputs or validation indicators (whats) and the ways to evaluate AI applications in agricultural mapping (hows). These indicators, validated by researchers (experts) with expertise in the study’s area of knowledge (e.g., agriculture and artificial intelligence), build the House of Quality.

3. Results

This study finds influential countries and collaborators in scientific production related to AI’s contribution to agricultural mapping and provides a trend analysis in this area of knowledge. It synthesises documents and applies QFD to determine strategies for AI’s contribution to agricultural mapping.

3.1. Performance Analysis

3.1.1. Scientific Contribution

Figure 2 shows the annual publications of studies on AI applications in agricultural mapping. In the first three decades, scientific production did not represent even 1% of the total production, while in the last thirty years, production has shown a moderate exponential growth that could be related to image processing automation and agricultural land performance globally. Furthermore, in recent decades, farmers’ domain knowledge has been merged with AI to improve agricultural decisions.

The studies’ citations show a growing trend and reached their highest peak in 2019 due to the adaptation and transition processes of intelligent technologies in agriculture.

3.1.2. Most Productive Countries

Table 1 shows the top five countries with the highest scientific production (36.66% of the total output), belonging to the continents of Europe, Asia, and North America. Additionally, it presents two types of publications: Single-Country Publications (SCPs), which represent cooperation between authors from the same country, and Multiple-Country Publications (MCPs), which represent cooperation between countries by authors from several countries. The MCP indices indicate that the USA has the most significant collaboration.

Furthermore, Figure 3 presents the five most predominant countries collaborating with other countries through a chord diagram with solid connections (collaboration ≥ 5 articles). The line thickness represents the number of connections between countries. Although China and India are among the five most productive countries, they are not among the top five countries with the most significant collaborations.

3.1.3. Keyword Co-Occurrence Analysis

Figure 4 shows the author keywords by group and their coexistence across the lines. The colour and intensity of the line identify the frequency at which these keywords coexist. The frequency of keyword coexistence highlights four groups: “artificial intelligence”, “cartography”, “remote sensing”, and “gis”. Therefore, the research aims to highlight the application of AI in agricultural mapping by fusing AI methods and geomatic tools. Also, topics of interest and those that are less developed, such as conservation and biodiversity in agricultural activities, are highlighted.

3.1.4. Trending Topics

Figure 5 presents the strategic diagram of the themes related to AI in agricultural mapping applications. These themes are distributed into four categories, depending on their importance and degree of development.

• (1). Topics of high development and importance (motor themes): “Land management” and “agricultural land” belong to this category, with significant studies in the recovery/enabling of agricultural soils to maintain or preserve rural sectors’ food security. “Random forest” and “sentinel-2” include studies of the most used classification algorithms and series of multispectral images in crop type mapping and vegetation detection. “Convolutional neural network” includes studies on the type/classification of LULC and the classification of agricultural soils’ physical parameters.

• (2). Themes developed without significant importance (niche themes) correspond to “soil moisture” and “sustainability”. They include studies on sustainable water resource management and drought event management.

• (3). New themes with a low level of importance (emerging themes) include “antigenic cartography” and “avian influenza”. These studies perform genetic and antigenic analyses of viruses through antigenic maps that allow the visualisation of the relationship between antigens and the cure antigenic coverage for poultry and livestock sectors. “Land consolidation” and “spatial distribution” include studies related to the spatial structure of crops to improve soil consolidation and contribute to agricultural management.

• (4). Basic and transversal research themes (basic themes): Themes related to “water quality” incorporate digital soil analysis studies, streams, and basins through mapping in an agricultural activity contexts. “Rural landscape” includes themes related to the spatial analysis of the ancient landscape of rural sectors characterised by the agricultural economy. “Artificial intelligence” includes studies on precision agriculture, biodiversity conservation, climate change, and agricultural land monitoring using ML/DL. “GIS” and “cartography” incorporate geospatial technology studies for mapping agricultural LULC.

3.2. Review

3.2.1. Classification of Topics Related to Agricultural Mapping

The review allowed the analysis of 206 documents related to the application of AI in agricultural mapping. Table 2 presents the distribution of the studies in six themes with their respective variables related to agricultural mapping. Agricultural activities/practices and LULC are the most predominant themes in this study.

3.2.2. Review Synthesis

Table 3, Table 4, Table 5, Table 6, Table 7 and Table 8 show the different AI methods, algorithms and learning types used in agricultural mapping. They also present geomatic tools and thematic maps and their predominant use in the topic of study. The distribution of countries is based on geography and scientific collaboration, starting with North America and then Europe, Asia, Latin America, Africa, and Oceania.

• Agricultural management

This topic comprises 38.83% of the scientific contribution regarding the use of AI in agricultural mapping. ML and DL are the most used AI learning methods, and ANNs, CNNs, and SVMs are the most used AI methods/algorithms. In addition, this highlights the use of geomatic tools such as GIS, RS, RPAS, and GNSS in the classification mapping of crop types, weeds, agricultural practices, and crop optimisation (Table 3).

93% of agricultural management documents consider crops to be the leading resource, and 7% highlight soil (e.g., those in Hungary), watersheds (e.g., those in France), and forests (e.g., those in Brazil). Also, agricultural management highlights the use of thematic maps that consider phenology, characteristics, and types of crops (76%), agricultural production estimate (10%), weeds (10%), and habitat suitability (4%). These maps frequently have a spatial resolution of 30 m (48%), 10 to 20 m (30%), 2.4 to 6 m (15%) and 60 and 90 m (7%).

Table 3

A summary of methods based on agricultural management documents.

Country	Methodology/Learning Type	Geomatic Tool	Map’s Use
		(GIS, RS, RPAS, LSS, and GNSS)	(Reference)
USA	ML/RF, MaxEnt	GIS (Google Earth Engine), GNSS (GPS), and RS (Landsat)	For sustainable practice selection.
			[42]
	DL/DNN	GIS and RS (Landsat 8, Sentinel 1A, MODIS)	For training data sets.
			[43]
	ML/RF, SVM	GIS (Google Earth Engine) and RS (Sentinel 1–2)	For crop type classification.
			[31]
	ML/Bayesian Models, ANN	GNSS (GPS) and RS	To encourage participatory design use and adopt more farmer-centred principles.
			[44]
	DL/RF, SVM, and CNN	RS (Landsat 7, 8)	To develop a classification model of sustainable and unsustainable agricultural practices.
			[18]
	ML/ANN, SVM	GIS (Trimble GeoSpatial) and RS (ASTER)	For main summer crop classification.
			[45]
	ML/SVM, RF, and GBRT	GIS and RPAS (Matrice 2010 DJI Quadcopter)	To determine nutrient concentrations in citrus fruits.
			[46]
	ML, SL/RF, SVM	GIS (Google Earth Engine) and RS (Landsat 5, 7, 8)	For the mapping of crop types at field level.
			[47]
	ML, DL/ANN, CNN	GIS, RS, and GNSS (GPS RTK)	As a weed mapping system.
			[48]
Canada	ML/ANN	GIS and RS (Polarimetric Synthetic Aperture Radar, RADARSAT-2)	For crop biomass estimation.
			[21]
	ML/SVM	GIS and RS (SPOT)	For satellite images time series.
			[49]
	ML	GIS (ArcGIS) and RS (Landsat)	For pollination supply/to improve crop yields.
			[50]
Spain	ML/ANN, SVM	GIS (SIGPAC, QGIS) and RS (Sentinel 1–2)	For the identification, classification, and phenological state of cultivation.
			[33]
	ML/ANN, SVM	GIS, RS (QuickBird, WorldView 2) and GNSS (GPS TRIMBLE PRO-XRS)	To discriminate and map infestations in sunflower crops.
			[51]
	ML/ANN, Maximum Likelihood and Spectral Angle Mapper	GIS and RS (WorldView 2, 3)	-
			[52]
	DL/CNN	GNS and RS	For crop growth status.
			[53]
Italy	ML/PCA	GIS and RS	To develop and optimise crop trait recovery models from hyperspectral data.
			[54]
	ML	GIS (Corine Land Cover) and RS (MODIS MOD09A1)	For rice cultivation phenological detection.
			[55]
Germany	ML/ANN	GIS, GNSS (GPS R10 Trimble) and LSS (HawkSpex Scan)	For leaf concentration prediction.
			[56]
Germany and Slovakia	ML/PCA	GIS and RS (PRISMA, Sentinel)	As a hybrid model for the recovery of non-photosynthetic biomass.
			For leaf concentration prediction.
			[57]
France	ML/Hidden Markov Models	GIS	For the relationship between cropping systems and landscape patterns.
			[58]
	ML/Markov logic networks	GIS (LPIS) and RS (Formosat-2)	To contribute to environmental impact assessment, agricultural management, and food security.
			[59]
	DL/Semantic Segmentation	GIS (QGIS), RPAS (Quadricopter UAV), RS, and GNSS	For vine disease detection.
			[60]
Hungary	ML/Computer-Aided Photo-Interpretation	GIS (LPIS) and RS (Ikonos, QuickBird)	For agricultural practice evaluation.
			[61]
Slovenia	DL/CNN	GIS and RS (Sentinel 2)	For cultivated land detection.
			[62]
Poland	ML/RF	GIS (PhotoScan-Agisoft), RS (Sentinel 2) and GNSS (MobileMapper 120)	For the identification of pine stock volume.
			[63]
Portugal	DL/Computer Vision, CNN	GIS	For dynamic phenological mapping.
			[17]
Belgium	ML/ANN	GIS	For pest monitoring.
			[64]
Sweden	ML/Genetic Algorithm	-	To contribute to the development of better agricultural practices.
			[65]
Netherlands	ML/SVR	GIS and RS (Sentinel 1, 2)	For crop growth.
			[66]
Austria, Belgium, Spain, Denmark, and the Netherlands	DL/CNN	GIS (LPIS) and RS (Sentinel 2)	For crop monitoring.
			[67]
China	ML/PCA, Ward’s Hierarchical Classification	-	For gross crop production.
			[68]
	ML, DL/CNN	GIS and RS (Sentinel 2)	For the detection of crop harvest stages.
			[69]
	DL/CNN	GIS, RS and RPAS (Polaris xp2020 Drone)	For seedling detection.
			[70]
	DL/CNN, Computer Vision	GIS and RS	For vegetable recognition and their size estimation.
			[71]
	ML, DL/Computer Vision, CNN	GIS	For the construction of agricultural disease data sets.
			[72]
	DL/YOLO-V5, CNN	GIS	For intelligent crop survival rate detection for agricultural yields.
			[73]
	ML/Computer Vision, CNN	GIS, RS and RPAS (UAV Inspire 1 DJI)	To optimise weed management in agriculture.
			[15]
India	DL/DNN	GIS	For spatial distribution and time series analysis.
			[74]
	ML/RF	GIS and RS (Sentinel 1, 2)	As an automated global crop classification model.
			[75]
	ML	GIS (Google Earth) and RS	To propose technological solutions to improve the productivity and sustainability of agriculture.
			[76]
	DL/CNN	GIS and GNSS (GPS)	For the diagnosis and prognosis of crop diseases.
			[77]
	DL/DCNN	GIS, GNSS (GPS), and RPAS (Amitasha Drone Quadcopter)	For pest detection in agricultural fields.
			[19]
	DL/CNN	GIS and RPAS (Drone)	For the detection and georeferencing of waste, weeds, and plant diseases.
			[78]
	ML/RF, SVM	GIS and RS (Sentinel 2)	For agricultural performance.
			[79]
Japan	ML/SVM, RF	GIS and RS (TerraSAR-X)	To discriminate and map different crop types.
			[80]
Iran	DL, ML/CNN	GIS, RS, and RPAS (Drone DJI Phantom 4 Pro)	For plant detection.
			[81]
Afghanistan	ML/ANN	GIS (ArcGIS) and RS (Landsat 8 OLI)	For grape yield prediction.
			[16]
Taiwan	ML/Things-Based Autonomous Mobile Robot System	RS	For the design and implementation of an Autonomous Mobile Robotic System for Pithaya Harvesting.
			[82]
Malaysia	ML/CNN	RPAS (Drone DJI Phantom 4 RTK), GNSS (GPS Trimble BD920) and RS (Landsat 8)	For land cover distribution.
			[83]
Korea	ML/SVM, RF	GIS (ArcGIS Pro), RPAS (UAV), and RS (Landsat)	For the classification and limitation of rice fields.
			[84]
South Korea	DL/CNN	GIS	To improve weed recognition.
			[85]
Brazil	ML/ANN	GIS, GNSS (GPS Trimble 2013 RTK), and RS	For the spatial and temporal monitoring of soybean cultivation biophysical characteristics.
			[86]
	ML/RF	GIS (ArcGIS)	To estimate the productive potential of macauba trees.
			[87]
	ML/RF, ANN and XGBoost	GIS and RS (Landsat OLI, Sentinel 2)	For agricultural intensification.
			[88]
Brazil and Venezuela	ML/Clustering Algorithm	GIS and LSS (LíDAR)	For the identification of different elements such as trunks, branches, and leaves.
			[89]
Argentina	ML/CNN	GIS (ArcGIS Pro), RPAS (UAV DJI Phantom 4 Pro), and GNSS(GPS)	For crop yield.
			[90]
Argentina, China, France, Madagascar, Morocco, Pakistan, Russia, South Africa, Ukraine, the USA	ML/RF, SVM	GIS (GEOGLAM) and RS (SPOT4, Sentinel-2 and Landsat 8)	For crop type production.
			[91]
Mali, South Africa, and Ukraine	ML/RF	GIS and RS (Sentinel-2, Landsat 8)	For the performance evaluation of the Sen2-Agri automated system.
			[92]
South Africa	ML/SVM, RF	GIS and RS (Landsat 8)	To differentiate crop types.
			[93]
Australia	ML/Fuzzy logic	GIS, RS, and GNSS (U-Blox5 GPS)	To demonstrate the accurate classification of livestock behaviours.
			[94]
	DL, ML/CNN, YOLO V3	-	For aphid colony detection.
			[95]
	ML/YOLO v4 CNN, XGBoost	GIS, RPAS (UAV), and RS (SPOT)	For pasture management, biological control, and herbicide use.
			[96]

Note—ML: machine learning. DL: deep learning. SL: Supervised Learning. DNN: Deep Neural Network. CNN: Convolutional Neural Network. ANN: Artificial Neural Network. PCA: Principal Component Analysis. XGBoost: Extreme Gradient Boosting. BRT: Boosted Regression Tree. SVM: Support Vector Machine. RF: Random Forest. GIS: Geographic Information System. RS: remote sensing. UAV: Unmanned Aerial Vehicle. LPIS: Land Parcel Information System. GPS: Global Positioning System. GNSS: Global Navigation Satellite System. (-) No recorded information.

• LULC

Table 4 shows the documents associated with agricultural LULC (21.36% of the scientific contributions). ML is the most used learning method. The frequent AI methods/algorithms in this topic are RF, SVM, and Fuzzy Logic in forest identification mapping, crop fields, and agricultural landscape precision.

LULC studies analyse the spatial distribution of agricultural territory as the leading resource (73%) through thematic maps with a predominant spatial resolution of 0.5 to 10 m (53%), 20 to 30 m (40%), and 60 m (7%). Furthermore, 20% of the studies correspond to forests, agricultural landscapes, and vegetation, and 7% to wetlands, greenhouses, and coastal environments, highlighting the mapping of agricultural classification with vegetation indices (e.g., the NDVI).

Table 4

A summary of methods based on LULC documents.

Country	Methodology/Learning Type	Geomatic Tool	Map’s Use
		(GIS, RS, RPAS, LSS, and GNSS)	(Reference)
USA	DL/DNN, RF, SVM, and CNN	RS (Landsat 7, 8) and RPAS (Drone)	To classify agricultural land use by exploiting EO data’s temporal and spectral dimensions.
			[97]
	ML/ANN	GIS (QGIS, ArcGIS and Google Earth Engine) and RS	For crop cover prediction.
			[98]
	ML/SVM	GIS and RS	To compare the effectiveness of SVM-BEE with other methods.
			[99]
Grenade	-	GIS	To analyse the anthropic impact on agricultural environments, infrastructure, and cultural meanings.
			[100]
Spain	ML/ANN	GIS (Geomedia Professional 5.1), GNSS (GPS TR GEOD L1/L2), and LSS (Vexcel UltraScan5000 Precision)	For LULC knowledge and its evolution over time.
			[101]
	UL/Unsupervised Classification	GIS (CORINE Project) and RS (NOAA Satellites, AVHRR Sensor)	To obtain changes in mapping caused in the forests.
			[102]
	SL, UL/Supervised and Unsupervised Classification	GIS (SIGPAC) and RS (Landsat 5)	Public administration needs to implement an agricultural cadastre.
			[103]
	ML/ANN	GIS	-
			[104]
	ML/ANN	GIS (ERDAS Imagine) and RS (Landsat)	The identification of types of land use and management.
			[105]
Italy	ML/Overlay	GIS (CORINE Land Cover, MOLAND, GoogleEarth 5.0) and RS (Quickbird)	The landscape recovery planning of farming terraces.
			[106]
	ML/Overlay	GIS and RS	The evaluation of consequences of rural land and landscape transformations.
			[107]
Germany and Slovakia	ML/SVM, Markov Random Field	GIS and RS (Ikonos)	The verification of crop and grassland soil classes.
			[108]
France	ML/Expert System	GIS and RS	To improve the relationship understanding between agriculture and the landscape.
			[109]
	ML/Conglomerate and PCA	GIS (QGIS v.3.4 and SAGA)	The site’s classification to determine hydrocarbon contamination.
			[110]
Cyprus	ML/Expert System	GIS (ArcGIS)	For land redistribution.
			[111]
Bulgaria	ML/Fuzzy Convolution Filter	GIS (Geodatabase, ArcGIS 9.2), RS and GNSS (GPS)	To evaluate human-induced soil transformations.
			[112]
Greece	ML/SVM	GIS, RS (Hyperion) and LSS (Hyperion VNIR Spectrometer)	The distribution and density of land cover categories.
			[113]
	ML/PCA, SVM	GIS (ArcGIS) and RS (Sentinel-2)	For LULC mapping highlighting wetlands.
			[23]
Poland	ML/RF	GIS, LSS (LíDAR), GNSS (GPS Mobile Mapper 120), and RS (Landsat, Sentinel)	For the conservation planning of natural and semi-natural habitats.
			[114]
	ML/RF	GIS (QGIS and ArcGIS), LSS (LíDAR)and RS (Sentinel 2)	For LULC class detection related to agriculture.
			[115]
Portugal	ML/RF, SVR	GIS (ENVI version 4.8) and RS (AISA Eagle, Hawk)	For Map shrub cover fractions.
			[116]
England	ML/RF	GIS (ArcGIS, SAGA), RS, and GNSS (GPS)	For the large-scale mapping of small landforms in agricultural landscapes.
			[117]
Ukraine	ML/Generalization Algorithm	GIS (StateGeoCadastre)	-
			[118]
Ireland	ML/RF, SVM	GIS (GRASS GIS 7.0) and RS (Landsat 8 OLI, RapidEye and TERRA-MODIS)	To evaluate and determine effective atmospheric correction strategies.
			[119]
Turkey	ML/SVM, Maximum Likelihood	GIS and RS (SPOT 5)	For agricultural yield estimation.
			[120]
China	ML, DL/RF, CNN, and Computer Vision	GIS and RS	For the precise mapping of agricultural landscapes and surface mining.
			[121]
Taiwan	ML/SVM, RF	GIS (ArcGIS), RS (WorldView-2), and GNSS (GPS)	To accurately identify and map tea crops.
			[122]
India	ML/Semantic Segmentation	GIS (QGIS, Copernicus Global Land Cover and Google Earth Pro) and RS (Sentinel 2)	For the remote sensing of photovoltaic solar farms.
			[123]
	ML/ANN, Fuzzy Logic	GIS (Google Earth Engine), RPAS (DJI phantom 3 professional), GNSS (GPS), and RS (Sentinel-2)	As a linear mixture model for crop surface mapping.
			[2]
	DL/Semantic Segmentation, CNN, and ANNP	GIS	The mapping and identification of single and multiple tree species.
			[124]
	ML/RF	GIS (QGIS) and RS (Worldview-2)	For mapping crop fields in heterogeneous agricultural landscapes.
			[125]
Cambodia	ML/SVM, RF	GIS (ArcGIS, Google Earth), RS (Sentinel), and LSS (LíDAR)	For cropland data accuracy assessment.
			[126]
Bangladesh	ML/RF	GIS (Google Earth), GNSS (GPS), and RS (Landsat ETM, NOAA)	For urban expansion identification.
			[127]
Jordan	ML/ANN	GIS (ENVI v.5.3) and RS (Landsat 7)	For urban expansion pattern prediction.
			[128]
Korea	DL/CNN	GIS (ArcMAp) and RS (Landsat 8)	For land cover classification.
			[129]
	ML/Extraction Algorithm	GIS, RS (Landsat) and LSS (LíDAR)	For cropland boundary extraction.
			[130]
Brazil and Venezuela	ML/RF	GIS and RS (Landsat, Radarsat, TerraSAR-X and Sentinel 2)	For the recognition of Amazonian coastal environments.
			[131]
Mexico	ML/RF, SVM, and ANN	GIS (ArcMAp 10.5, Google Earth Pro, QGIS 3.10), and RS (Landsat 8)	For the assessment of conservation impact and vegetation cover sustainable management.
			[24]
	ML/Genetic Algorithm	Gis (ArcGIS versión 10.1) and RS	For niche modelling for a set of endangered top predators.
			[132]
	SL/Overlay	GIS (Google Earth Pro 7.3.4, QGIS 3.8.3), and RS (Landsat 5, 8)	The region’s inhabitants drive the determination of agricultural and forestry land use.
			[133]
Tunisia	SL/RF, K-Dimensional Trees K-Nearest Neighbours	GIS (Google Earth) and RS (Sentinel 2)	For land use management potential.
			[134]
	SL/RF, SVM	GIS and RS (SPOT 6)	To improve agricultural land cover classification.
			[135]
South Africa	ML/RF, SVM	GIS and RS (SPOT-4, Landsat-8)	To understand how class proportions and training set size influence the accuracy of cropland classifiers.
			[136]
Australia	ML/RF, SVM	GIS (Google Earth Engine, RS (Landsat 8-OLI), and GNSS (GPS)	To develop and provide an accurate land extension product.
			[137]

Note—ML: machine learning. DL: deep learning. SL: Supervised Learning. DNN: Deep Neural Network. CNN: Convolutional Neural Network. ANN: Artificial Neural Network. ANNP: Artificial Neural Network Deep. PCA: Principal Component Analysis. SVM: Support Vector Machine. RF: Random Forest. GIS: Geographic Information System. RS: remote sensing. GPS: Global Positioning System. GNSS: Global Navigation Satellite System. NOAA: National Oceanic and Atmospheric Administration. (-) No recorded information.

• Water management

This topic corresponds to 15.05% of the scientific contribution related to irrigation mapping, detecting potential groundwater areas, and evaluating water quality (Table 5).

Groundwater (66%) and surface water from rivers, basins, and wetlands (34%) are the leading resources for water management studies. The thematic maps of these investigations guide the spatial distribution, contamination, quality, and vulnerability of human/agricultural groundwater consumption. Also, consider the quality parameters, morphology, and inflows and outflows of surface waters. These self-organizing maps have spatial resolutions of 30 m (56%), 10 to 20 m (33%), and 50 to 60 m (11%).

Table 5

A summary of methods based on water management documents.

Country	Methodology/Learning Type	Geomatic Tool	Map’s Use
		(GIS, RS, RPAS, LSS, and GNSS)	(Reference)
USA	DL/Semantic Segmentation, ANN	GIS and RS (Sentinel-2)	Mapping of irrigation centre pivots.
			[138]
	ML/ANN, GBRT	GIS (MODFLOW/MODPATH) and RS	Metamodeling for groundwater age prediction.
			[139]
Canada	ML/Back-Propagation Neural Network and SVM	GIS, RS (Landsat 8) and GNSS (GPS GARMIN 76CSx)	Concentration quantification surface water quality parameters.
			[140]
Spain	ML/ANN, RF and SVM	GIS (ArcGIS), GNSS (GPS) and RS (Landsat 8-OLI)	Potential areas detection of groundwater for irrigation and domestic consumption.
			[141]
Italy	ML/RF, SVM	GIS (Corine Land Cover, ArcGIS) and GNSS (GPS)	Groundwater sustainable evaluation for human consumption and agriculture.
			[142]
Portugal	ML/PCA	GIS (ArcGis 9.3) and GNSS (GPS Trimble GeoExplorer)	Risk due to nitrate contamination.
			[143]
Denmark	ML/Ensemble Testing	GIS (ArcMap, CORINE 2012) and RS (Landsat 8)	Predict artificially drained areas.
			[144]
Austria and Germany	DL	GIS (ArcGIS) and RS (Sentinel 2)	Irrigation water demand
			[145]
Turkey	ML/ANN, Adaptive Neuro-fuzzy Inference System (ANFIS)	GIS (ArcGIS 10.2)	Spatial distribution of groundwater quality indices.
			[146]
	ML, DL/ANN	GIS and RS	Identification of alluvial terrain with different soil properties.
			[147]
	UL/SOM-ANNs	GIS and RS	Evaluation of water quality parameters.
			[148]
	UL/SOM, ANN and K-Means Clustering	GIS	Variables analysis that intervene in the quality of surface waters.
			[149]
China	ML/ANN, SVM and CNN	GIS (QGIS Desktop, ERDAS Image) and RS (Landsat 8 OLI)	Identification of geographical area reformed by water expansion.
			[150]
	SL/ANN, BPNN and ANFIS	GIS	-
			[151]
	ML/RF, KNN	GIS (ERDAS IMAGE 9.2), GNSS (GPS) and RS (Landsat 8, Radarsat-2)	Classification and mapping of forested wetlands.
			[152]
India	ML/ANN	GIS	-
			[153]
Iran	ML/ANN	GIS (ArcGIS Pro 2.9) and RS	Suitable site location for artificial groundwater recharge.
			[154]
	ML/SVM, Genetic Algorithm	GIS (ArcGIS 10.5, ENVI 5.3) and RS (Landsat 8)	Suitable site identification for rainwater collection.
			[155]
	SL, UL/SVM	GIS	Groundwater vulnerability mapping.
			[156]
	ML/ANN, Genetic Algorithm and SVM	GIS and RS (Landsat-8 OLI)	Build regression models to determine water salinity.
			[157]
	ML/Swarm Intelligence	GIS	Simulate and optimise multiple crop planning.
			[25]
	ML/SVM, RF	GIS (ArcGIS 10.8) and RS (Sentinel 2)	Water quality assessment.
			[158]
Japan	ML/RNNs	GIS	Identification of water quality dynamics.
			[159]
Vietnam	ML/Modified RealAdaBoost, SVM and RF	GIS (ArcGIS) and RS	Groundwater potential mapping.
			[160]
	ML/RF, AdaBoost Ensemble and MultiBoost Ensemble	GIS (ArcGIS) and RS	Build groundwater potential.
			[161]
Malaysia	ML/Fuzzy logic	GIS	Event-based stormwater runoff modelling for a tropical basin.
			[162]
Pakistan	ML	GIS (QGIS) and RS (Sentinel 2, Landsat 5)	Interaction between agricultural landscape, river morphodynamics and population settlements.
			[163]
Brazil	DL/DCN, ANN	GIS (Google Earth Engine) and RS (Landsat 5)	Pivot irrigation systems automatic detection.
			[29]
Tunisia	SL/Genetic Algorithm, SVM	GIS and RS (Sentinel 2A)	Vulnerabilities identification in groundwater aquifers.
			[164]
Australia	DL/CNN	GIS (ArcGIS), LSS (LíDAR) and RS (Landsat 5, 7)	Detect farm dams.
			[165]

Note.—ML: machine learning. DL: deep learning. SL: Supervised Learning. CNN: Convolutional Neural Network. ANN: Artificial Neural Network. SOM: Self-organizing map. PCA: Principal Component Analysis. BRT: Boosted Regression Tree. SVM: Support Vector Machine. RF: Random Forest. GIS: Geographic Information System. RS: remote sensing. GPS: Global Positioning System. GNSS: Global Navigation Satellite System. (-) No recorded information.

• Agroclimatic Risks

Table 6 shows documents related to mapping vulnerabilities and risks of agricultural and natural spaces that use AI methods/learning types/algorithms and geomatic tools for agrarian management (12.62% of the scientific contributions).

Of these studies, 50% explore agricultural territory and forests as their primary resource. The predominant risks associated with these resources are forest fires (17%), gully erosion and land subsidence (26%). Additionally, 25% of the studies analyse hydrographic basins, and another 25% analyse crops. The risks related to these resources are the susceptibility to floods (39%), drought and contamination by heavy metals (18%). The predominant spatial resolution of the thematic maps is 10 to 30 m.

Table 6

A summary of methods based on agroclimatic risk documents.

Country	Methodology/Learning Type	Geomatic Tool	Map’s Use
		(GIS, RS, RPAS, LSS, and GNSS)	(Reference)
USA	DL/ANN	GIS (ArcGIS Pro) and RS	For high-risk area identification for mitigation.
			[166]
Spain	ML/RF	GIS, RS (Sentinel 1), and GNSS (GPS)	To evaluate the vulnerabilities and risks of agricultural and natural spaces.
			[167]
Germany	-	GIS (APGIS, Corine Land Cover 2018) and LSS (LíDAR)	For agricultural spatial planning.
			[168]
	ML/K-Nearest Neighbour	GIS (Corine Land Cover) and RS (MODIS)	For the identification of duration, extent, and drought severity.
			[169]
Greece	ML/SVM	GIS (Corine 2000) and RS (MODIS, SPOT 4 and ASTER)	For post-fire evaluation in Mediterranean areas.
			[170]
	ML/RF, XGBoost	GIS (Corine Land Cover, QGIS) and RS (Sentinel 1B)	In assessing flood susceptibility.
			[171]
	ML/SVM, ANN	GIS (QGIS) and RS (Sentinel 1, 2)	For mapping natural and man-made disasters.
			[172]
Poland	ML/RF, GBM	GIS (ArcGIS 10.2, Corine 2018) and RS	For the detection of forest fire occurrence.
			[173]
Turkey	ML/RF	GIS and RS (Sentinel-2, ENVISAT-ASAR)	In flood mapping for decision-making.
			[174]
	ML/MANN, GANN, RBANN	GIS (ArcGIS 10.2.1) and RS	In flood flow prediction
			[175]
	ML/NGBoost, RF, and XGBoost	GIS (QGIS, Corine 2018) and RS	For assessing flood susceptibility.
			[176]
Iran	ML/RF, BRT	GIS (ArcGIS) and RS	For the determination of risks due to land subsidence.
			[177]
	ML/Fuzzy Logic	GIS (ENVI), GNSS (GPS), and RS (Sentinel 1A)	In sinking area detection.
			[178]
	ML/ANN, RF	GIS (Google Earth) and RS (Landsat 8-OLI)	In land subsidence location.
			[179]
	ML/AdaBoost	GIS (ArcGIS 10.3, ENVI 5.4) and RS (ALOS, Landsat 8)	In gully erosion susceptibility mapping.
			[180]
Brazil	ML/Fuzzy logic	GIS (Arc View) and RS (Landsat)	For the monitoring and control of deforestation and fire areas.
			[181]
	ML/ANN, SVM	GIS and RS (Landsat 8, Sentinel 2)	In flood distribution identification to avoid contamination.
			[28]
Egypt	ML/Fuzzy Logic	GIS (ArcGIS 10.4), RS (Sentinel 2A), and GNSS (GPS)	For assessing agricultural soil contamination.
			[182]
Morocco	ML/RF, Boosted Regression Trees (BRTs), and SVM	GIS (Google Earth), RS (Landsat 8-OLI, ASTER), and GNSS (GPS)	For the location of gully erosion sites.
			[183]
South Africa	ML/RF, SVM	GIS (Google Earth Engine) and RS (MODIS Terra, Landsat 7–8)	To identify the drivers of drought.
			[184]
Australia	ML/RF, FL, SVM, CART, and BRT	GIS and RS (Landsat 8)	In agricultural drought inventory.
			[32]
	ML/Fuzzy Logic and Semantic Matching	GIS (ArcGIS 10.1) and RS (TERRA, AQUA)	To provide recommendations and support for decision-making in sustainable agriculture.
			[185]
	ML/Cubist	GIS and RS (MODIS)	To understand the magnitude and distribution of soil loss due to water erosion.
			[186]

Note—ML: machine learning. DL: deep learning. ANN: Artificial Neural Network. SOM: Self-organizing map. GBM: Gradient Boosting Model. XGBoost: Extreme Gradient Boosting. BRTs: Boosted Regression Trees. SVM: Support Vector Machine. RF: Random Forest. GIS: Geographic Information System. RS: remote sensing. GPS: Global Positioning System. GNSS: Global Navigation Satellite System. (-) No recorded information.

• Pedology/Edaphology

This topic corresponds to 10.19% of the scientific contributions, highlighting publications associated with soil monitoring mapping, the classification of agricultural soil parameters, and soil prediction (Table 7).

The leading resource of the studies associated with the pedology/edaphology topic is the soil (80%), followed by crops (20%). These studies use the mapping of soil types (31%), soil properties such as salinity (54%), and land subsidence coverage (15%). The spatial resolution of these mappings ranges from 10 to 30 m.

Table 7

A summary of methods based on pedology/edaphology documents.

Country	Methodology/Learning Type	Geomatic Tool	Map’s Use
		(GIS, RS, RPAS, LSS, and GNSS)	(Reference)
USA	ML/ANN, RF, SVM, and GBM	GIS (ArcGIS) and RS (AVHRR)	For soil property prediction and maize yield.
			[187]
Hungary	ML/RF	GIS (QGIS v.3.14)	In the national landslide registry.
			[188]
Ukraine	ML/Fuzzy Logic	GIS and RS (Landsat 7, ASTER GDEM)	To assess soil texture distribution and water retention properties.
			[189]
Lithuania	ML/CNN	GIS (LPIS) and RS (Sentinel 2)	For soil monitoring.
			[190]
China	ML, DL/DCN, RF, and ANN	GIS (ArcGIS 10.1) and RS (GF-1 WFV Sensor, ASTER)	For geoplot mapping.
			[30]
	DL/Mask-RCNN	GIS, LSS (GX750-HDR GPR), RS, and GNSS (GPS)	For agricultural soil parameters classification.
			[191]
	ML, DL/ANN, CNN, RF, and XGBoost	GIS (ArcGIS) and RS (ASTER GDEM, MODIS MOD13Q1 and SPOT 4)	For soil property identification.
			[192]
	ML/SVM, ANN, and RF	GIS, RS (Sentinel-2A), and GNSS (Trimble JUNO GPS)	For mapping soil salinity in arid areas.
			[193]
	ML, DL/XGBoost, CatBoost, and TPE-CatBoost	GIS (Google Earth Engine, ArcGIS 10.8.1) and RS (SMAP)	For the spatial estimation of soil moisture in maize-producing areas.
			[194]
Iran	ML/ANN	GIS (ArcGIS)	For the spatial modelling of soil electrical conductivity.
			[13]
	ML/BRT, XGB	GIS and RS (Sentinel 1A, ASTER-DEM)	For land subsidence rate detection.
			[195]
Afghanistan	ML/Fuzzy Expert System	GIS (ArcGIS, Google Earth Engine) and RS (Landsat 8 OLI)	To assess land suitability for potential vineyard extension.
			[196]
Brazil	ML/SVM, ANN	GIS and RS (YARA Sensor, ALS Sensor)	For nitrogen measurement to improve agricultural productivity.
			[197]
	ML/ANN	GIS and RS	In soil prediction.
			[198]
Chile	ML/RF	GIS and RS (Landsat 5, 7)	In evapotranspiration estimation.
			[199]
Mexico	ML/Decision Tree, Computer-Aided Mapping and Multinomial Logistic Regression	GIS (ArcView 8.1, IDRISI) and GNSS (GPS)	For local soil class evaluation with landscapes and climatic conditions.
			[200]
	ML/ANN	GIS (ArcView 8.1 e IDRISI) and RS (Landsat ETM)	In land use change identification.
			[201]
South Africa	ML	GIS, GNSS (GPS), and RS	In agricultural and environmental management.
			[202]
Australia	ML/ANN, BPNN	GIS and RS (Landsat 7, ETM+ Sensor)	For dryland salinity mapping.
			[203]

Note—ML: machine learning. DL: deep learning. CNN: Convolutional Neural Network. ANN: Artificial Neural Network. SOM: Self-organizing map. GBM: Gradient Boosting Model. XGB: Extreme Gradient Boosting. BRT: Boosted Regression Tree. SVM: Support Vector Machine. RF: Random Forest. GIS: Geographic Information System. RS: remote sensing. LPIS: Land Parcel Information System. GPS: Global Positioning System. GNSS: Global Navigation Satellite System.

• Public management

Table 8 shows the mapping studies of public management (1.94% of the scientific contributions). It highlights ML with ANN use and geomatic tools such as GIS and RS for agricultural decision-making.

The leading resource of these studies is cultivation. Also, mapping guides the evaluation of crops through NDVI maps (25%), the identification of routes for agricultural machinery (50%), and the quality of farm products (25%).

Table 8

A summary of methods based on public management documents.

Country	Methodology/Learning Type	Geomatic Tool	Map’s Use
		(GIS, RS, RPAS, LSS, and GNSS)	(Reference)
Italy	ML/ANN	GIS (Corine) and RS (Landsat TM/ETM, NOAA-AVHRR)	In interannual variation evaluations of crop areas on a regional scale.
			[204]
India	ML	GIS, RPAS (Drones agrícolas), GNSS (GPS), and RS	In decision-making in agriculture.
			[205]
Iran	ML/Particle Swarm Optimisation (PSO), ANN and SOM	GIS	In the identification of agricultural machinery parts.
			[206]

Note—ML: Machine Learning. ANN: Artificial Neural Network. SOM: Self-organizing map. GIS: Geographic Information System. RS: remote sensing. GPS: Global Positioning System. GNSS: Global Navigation Satellite System. NOAA: National Oceanic and Atmospheric Administration.

• AI procedures in agricultural mapping

The Table 9 shows the most relevant (current) AI procedures in agricultural mapping, according to the cases mentioned in Table 3, Table 4, Table 5, Table 6, Table 7 and Table 8.

3.3. Artificial Intelligence’s Contributions in Agricultural Mapping (QFD)

The House of Quality (HoQ) enabled the establishment of indicators that validate AI’s contributions to agricultural mapping. Figure 6 shows the relationship between quality indicators and their requirements based on the opinion of ten experts. This analysis found 11 indicators and 17 requirements. Therefore, each expert performed 187 validations. The experts identified the indicators’ importance, with the most relevant being the optimisation of agricultural processes and production, agroclimatic risk prevention, remote sensing and geolocation, image processing, digitisation, knowledge generation, route optimisation, and agricultural monitoring and control.

Additionally, the HoQ found highly significant relationships between remote sensing and geolocation with the fusion of AI and geomatics tools, photogrammetry processes, georeferencing, and the application of neural networks. The optimisation of agricultural processes and production is related to big data, management tools for agricultural monitoring and control, pattern identification algorithms, technological development, and the generation of apps. Also, image processing in agricultural activities is highly related to using geometric tools, training algorithms, learning, classification, pattern identification, and georeferencing.

The correlation matrix (the Roof of the House of Quality) specifies the correlation between the quality parameters. It also highlights strong positive correlations between the fusion of geomatic tools with AI, big data, and technological development. The incidence of using geomatic tools correlates to the processes of photogrammetry and georeferencing. The training and learning algorithms correspond significantly to image classification, pattern identification, and vegetation indices. The importance weights of the quality indicators formulate strategies for the contributions of AI to agricultural mapping including the following:

• Provide a data set of agricultural soil properties and behaviour to establish AI soil prediction models that optimise and guarantee environmental sustainability.

• Use ANNs/CNNs to help with identification, geolocation, crop counting, fertiliser prescription, and biological controllers.

• Merge geomatics tools and artificial intelligence techniques to detect real-time agricultural pests.

• Promote high-performance technologies such as big data, geomatic tools, and pattern classification/identification algorithms to predict agricultural production and identify sustainable agroclimatic zones, which will guide farmers’ and producers’ decision-making.

• Generate apps related to intelligent irrigation systems and early warnings to contribute to planning optimal routes to improve food security.

• Automate agricultural control and monitoring through the Internet of Things (IoT), AI and multispectral and hyperspectral techniques to strengthen agrarian management.

4. Discussion

This review provides predominant approaches in agricultural mapping (e.g., agricultural management, agrarian LULC, and water management) and the synergy of AI applications (e.g., ML and DL) with geomatics tools (e.g., GIS, RS, and RPAS) to optimise agricultural resources, predict/manage crop yields, and ensure food security. The agricultural mapping environment with these tools helps decision-makers gain control of their products from planting, production, and harvesting.

AI in agricultural mapping begins with geography, rural landscapes and farming structures (Figure 2). That is, in analysing the spatial relationships and organisation of areas farmers exploit, the application of AI in agricultural mapping influences agricultural management activities, LULC, and water management (75% of the total contributions). However, AI is not often used in agroclimatic risk activities, pedology/edaphology, and public management (25% of the total contributions) (Table 2). In agricultural mapping processes, the predominant geomatic tools are GIS (e.g., ArcGIS and Corine Land Cover), RS (e.g., Sentinel 1-2 and Landsat 8), GNSS (e.g., GPS), and RPAS (e.g., drones).

AI models and geomatics tools contribute to improving agricultural performance, environmental performance, and food security. For example, the study of [207] improved the ability to estimate China’s agricultural production through an optimisation algorithm with an accuracy of between 99.79% and 99.99%. The algorithm considered the national agrarian output of recent years and modelled it continuously to achieve a greater optimisation capacity. The study by [208] estimated Pakistan’s fruit production through a CNN with accuracies of 65.6% to 76.3%. Due to its relationship with population growth, this model could improve predictions for this country and developing countries. Also, the study by [209] analysed the improvement in banana yields at a global level using ML techniques such as ANNs that consider this crop’s reproductive growth traits. On the other hand, the study of [210] used ML through ANNs and SVMs for pest detection, identifying the outline of insects and achieving an accuracy of 90% and 91.5% for pest recognition. Researchers in [211] improve the previous method using UAVs based on ML and DL for pest identification, which had an accuracy of 99.55%. This method uses CNNs, which improves accuracy through image resizing and data set augmentation.

Regarding mapping in agricultural management, the USA has the most significant scientific contribution, using machine learning (67%), deep learning (33%), and geomatics tools such as GIS, GNSS, and RS (Landsat 7–8; Sentinel 1–2) in mapping studies associated with crop classification [31], the automated mapping of crop types through the Cropland Data Layer (CDL) and the Seasonal Crop Data Layer (IDCL) [212], sustainable agricultural practices [18], and nutrient concentrations [46], as seen in Table 3. These studies report an accuracy of over 80% in crop classification and sustainable agricultural practices. On the contrary, China and India use machine learning (30%) and deep learning (70%) with geomatics tools such as GIS, RS, and RPAS (e.g., drones) for mapping studies associated with crop yield optimisation [73,76], pest and weed identification [15,77]. These studies achieved pest and weed identification accuracies greater than 88%. Additionally, Latin American countries such as Brazil and Argentina base their agricultural mapping studies on estimating the productive potential of crops [87,90], reaching an average reliability of 71%. In these studies, machine learning is the most used learning technique, with geomatics tools such as GIS, RS, GNSS, and RPAS.

The mapping studies associated with LULC use AI through machine learning with ANN methodology and geomatics tools such as GIS, RS, and LSS in various agricultural land use activities (Table 4). For example, in Spain and Mexico, the mapping of changes caused by forests [102], the conservation/sustainable management of vegetation cover [132], and agricultural cadastre implementation driven by the inhabitants of the region are obtained [101]. These studies use unsupervised classification algorithms to generate information and establish limits on training sites. On the contrary, in India, mapping crop fields in heterogeneous agricultural landscapes is relevant [2]. Using supervised classification improves the accuracy of the estimated crop area.

Regarding mapping studies related to water management, AI is used in Iran through machine learning with SVM-ANNs and geomatics such as GIS and RS to identify suitable surface and groundwater sites (Table 5) [154]. In Turkey, using SOM-ANNs is relevant for evaluating the quality of this type of water by identifying contaminants [148]. These studies confirm that AI accurately determines the identification and evaluation of water resources (with an accuracy greater than 90%). In contrast, China uses machine learning with ANNs to estimate water scarcity in agricultural sectors [151].

Mapping studies associated with agroclimatic risks highlight the use of AI through machine learning with classification algorithms such as RF and geomatic tools such as GIS and RS for spatial risk analysis in agricultural contexts (Table 6). For example, in Iran, AI allows the spatial estimation of the vulnerability of land subsidence risks in agricultural territories [177]. In Turkey, flood mapping (with an accuracy greater than 90%) successfully determines disaster management policies and plans [175]. By contrast, in Australia, Germany, and Brazil, AI enables risk mapping for droughts, fires, and deforestation [169,181].

Regarding pedology/edaphology and public management activities, there are few studies related to the use of AI in countries such as China, Iran, Brazil, and Mexico (12%) (Table 7 and Table 8). China and Brazil use AI (ML with ANNs and CNNs) to generate soil maps, analysing properties such as carbon contents, texture, humidity, and salinity to improve agricultural production systems and food security [192,194,198]. These studies demonstrate better soil mapping than studies by the researchers of [213,214] based on methodologies such as interpolations and regressions.

Two-thirds of investments in agricultural projects are private, such as implementing irrigation systems [215] and ecological conservation [216], which is attributed to the innovative technology used by this sector. However, because rural communities cannot always sustain investments, the remaining one-third of investment corresponds to the public sector. Therefore, new knowledge and technologies are crucial for managing agricultural mapping, which contributes to the decision-making of political and private decision-makers in the agri-food sector [190].

Furthermore, the frequency of AI methods being used in agricultural mapping has increased in the last two decades, which could be associated with countries’ scientific contributions (Figure 2). This study finds that the most frequently used AI methods/algorithms in agricultural mapping are RF (24.76%), ANNs (22.82%), SVMs (21.36%), CNNs (14.08%), Computer Vision and Fuzzy Logic (8.74%). Similarly, the study of [217] shows that CNNs, SVMs, and You Only Look Once (YOLO) are most frequently used in disease and pest detection and prediction mapping. Furthermore, the study of [218] demonstrated the frequent use of SVM/SVR in the predictive mapping of biomass and bioenergy production processes. Other authors [219] highlight the frequent use of ANNs, RF, and SVMs in agricultural topics such as soil humidity, water salinity, and rural resource management mapping.

Overall, this review found that the predominant learning types in agricultural mapping are ML and DL. These learning types are applied in diverse geographic scopes because agroclimatic conditions, agricultural practices, the farm environment, and the types of crops identify many areas, regions, and countries. Furthermore, the study by [220] ensures that developed countries use AI in agricultural data analysis, while the use of these technologies is low in emerging countries.

ML is the most used AI learning due to its comprehensive training data and precision in identifying crops, agricultural resources, soils, pests, and diseases. However, the study of [221] indicates that DL has considerably increased its use in detecting the quality of agricultural products. Also, the study of [222] denotes DL as the universal learning method because it processes large amounts of data through matrix operations.

The advantages of AI methods in agricultural mapping focus on optimising resources, reducing labour, reducing the risk of environmental contamination and natural hazards, farm sustainability, and integrating technologies. The study by [223] confirms that AI changes how we grow and produce food. Drawbacks of using AI in agricultural mapping include monitoring issues due to crop size, extreme weather conditions, a lack of interoperability, availability, data integrity, and security.

Finally, this study considered QFD to be a comprehensive methodology for improving AI’s contribution to agricultural mapping. However, the Analytical Hierarchy Process (AHP) could complement these studies [224]. Similarly, other studies emphasise the integration of AI technologies with big data [225], the Generalised Representation of the Agro-Food System (GRAFS) approach [226], and the AHP [227] for decision-making contributions in the agricultural sector.

5. Conclusions

This study identifies ML (76%) and DL (24%) as the most prevalent AI learning types in agricultural activities. The most commonly used AI algorithms/methods in agricultural mapping are RF, ANNs and SVMs (with ML), CNNs, DNNs, and Computer Vision (with DL). Of the studies, 60% are related to agricultural management and LULC in prominent countries such as China, the USA, India, Spain, and Mexico. AI contributes to agricultural mapping and management activities in agricultural production, disease control and mitigation, and crop identification or classification. Additionally, AI highlights its use in LULC mapping studies associated with forest dynamics, agricultural management, and agricultural land cover improvements. Also, GIS, RS, RPAS, and GNSS are geomatic tools for planning and generating agricultural cartography.

Of the studies analysed, 38% highlight issues associated with water management, agroclimatic risks, and the pedology/edaphology of crops in countries such as Turkey and Iran. AI improves irrigation system mapping in agriculture, detects underground/surface water, and evaluates water quality for domestic consumption and cultivation. Also, AI contributes to mapping, detecting and reducing agroclimatic risks such as droughts, fires, floods, and land subsidence. Regarding pedology/edaphology activities, AI techniques present advances in soil suitability mapping and soil property analysis to improve agricultural performance.

The types of learning, AI techniques, and geomatic tools contribute to the improvement of agricultural production through the speed of control processes in the cultivation phases, reliability, and incredible precision of agricultural performance, considering various regions and environmental conditions in the improvement or formulation of new policies so that farmers achieve sustainable agriculture. These technologies identify and classify pests and weeds through image processing, reducing unnecessary plants in less time and minimising using fertilisers and herbicides that degrade and contaminate the soil. Furthermore, AI makes it possible to evaluate the groundwater quality for human/agricultural consumption with proactive conservation measures and contributes to global problems of water scarcity, drought, and the effects of climate change. These technologies allow the extraction of information from historical maps to identify wetlands and river paleochannels for water storage and to detect burned areas to avoid fire risks.

This review finds a deficit in the use of AI in public management activities such as crop estimation, quality control, and the distribution-marketing of agricultural products. Furthermore, this study does not cover potential areas, such as food production and the challenge of agriculture’s impact on the environment. On the other hand, there is no research related to AI in the agriculture–environment dualism. Therefore, this review proposes future lines of research related to applying AI techniques, such as IoT, in post-harvest agricultural activities, as well as developing precise quality management models and the development of AI technologies for sustainable agriculture.

Author Contributions

Conceptualization, G.H.-F. and P.E.-P.; methodology R.E., G.H.-F., J.L.R.G. and P.E.-P.; software, G.H.-F. and P.E.-P.; investigation, R.E., G.H.-F., J.L.R.G. and P.E.-P.; writing—original draft preparation, G.H.-F., P.E.-P. and R.E.; writing—review and editing, G.H.-F., J.L.R.G. and P.E.-P.; supervision, R.E. and G.H.-F. All authors have read and agreed to the published version of the manuscript.

Institutional Review Board Statement

Not applicable.

Data Availability Statement

Not applicable.

Acknowledgments

The authors thank the project ‘Generation of base information for irrigation and drainage projects in the Galapagos Islands’ of the Consejo de Gobierno del Régimen Especial Galápagos (CGREG) and the Centro de Investigaciones Rurales (CIR) of ESPOL for their support in the planning and management.

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. Study phases.

Figure 2. Scientific contributions: (a) the annual publications from 1957 to 2023; (b) The increase in publications from 1990 to 2023.

Figure 3. A chord diagram of the top five countries with the most significant collaborations.

Figure 4. The keyword co-occurrence analysis.

Figure 5. A strategic diagram of trending topics related to AI in agricultural mapping applications. Motor, niche, emerging, and basic themes show the study themes’ importance (centrality) and degree of development (density).

Figure 6. The House of Quality validating the contributions of AI to agricultural mapping.

Table 1

The most productive countries in the subject of study.

Country	Articles	* SCP	* MCP	Total Citations
Spain	79	69	10	1377
Italy	73	57	16	1172
USA	60	37	23	1672
China	60	48	12	943
India	36	33	3	614

* SCP: Single-Country Publications, MCP: Multiple-Country Publications.

Table 2

The reviewed studies’ classifications according to the agricultural themes.

Themes	Variables	Publications
Agricultural management	Land preparation. Fertilisation. Control of pests and diseases. Crop health and performance. Sustainable management. Phenology monitoring Cultural practices. Harvest. Crop rotation.	80
LULC	Agricultural landscape. Coverage and use. Territorial regulation. Agricultural frontier change. Historical LULC.	44
Water management	Water quality. Reservoir optimisation Irrigation systems.	31
Agroclimatic risks	Floods, droughts, frosts, and desertification. Water deficiencies. Deforestation. Forest fires. Alterations in controllers and biological threats. Ecological changes. Soil and water pollution from agricultural activities. Carbon capture. Early warnings. Land erosion.	26
Pedology/Edaphology	Soil classification and suitability. Soil properties. Soil topography.	21
Public management	Prediction of harvest and requirements. Quality control and traceability. Postharvest control, distribution, and marketing.	4

Table 9

A summary of AI procedures in current agricultural topics.

AI Method/Learning	Procedure	Theme	Application
ML/DL	- Historical cartography, Digital Elevation Models. - The extraction of mounds/rivers using DL detectors. - Mounds identified as archaeological sites.	Enhance archaeological sites through a historical hydrological network.	The historical cartography of burned areas in Portugal. The mapping of river paleochannels in India.
DL	- Preparation of the data set. - Training using DL models, Explainable Artificial Intelligence (XAI), and the Grad-CAM algorithm. - The validation of image recognition models.	Intelligent agricultural support systems (harvesting fruit and eliminating poor quality fruits).	The agricultural harvest pitaya in Taiwan, and rice, maize, soybeans, and apples in China. The phenological monitoring of vegetable crops in Portugal.
ML/RF/XGBoost	- Flood conditioning factors (Slope, NDVI, LULC and flood points). - Training through XGBoost. - Optimisation (Artificial Bee Colony) and validation.	Flood susceptibility mapping.	Flood mapping by river basins in Spain, Italy, Greece, and Turkey.
ML/SVM, RF	- Chemical factors conditioning water quality. - Data interpolation in ArcGIS. - Prepare a water quality map with SVM/RF. - The validation of mapping with the mean absolute error.	Groundwater quality mapping.	The mapping and monitoring of groundwater quality in urban and rural areas of Iran, Turkey, and Greece due to droughts. The sustainable use of groundwater resources for human consumption and agriculture in Mexico, Brazil, and Italy.
ML	- The behaviour modelling of bees. - A pollination model for crop production. - The application of the Artificial Intelligence Framework for the Environment and Sustainability (ARIES). - Sensitivity analysis using variances and Gaussian regression.	Mapping ecosystem services for crop yields in agricultural landscapes.	Maize and wheat crop yield optimisation in Colombia, Canada, the USA, and China.
ML/ANN	- The acquisition/processing of agri-food data. - An ML algorithm using ANN automatically trains crop rotation patterns from the Cropland Data Layer (CDL) time series. - The spatial estimation of seasonal crop distribution.	The monitoring of seasonal and permanent crop types.	The mapping of citrus crops in Spain, and of sorghum and finger millet in India.
ML/RF, ANN, and XGBoost	- The creation of synthetic samples. - Hierarchical classification. - The generation of spectral indices using RF. - The training of ML algorithms (ANN and XGBoost). - Precision evaluation.	Agricultural intensification.	The mapping of the agricultural intensification of rice, beans, and soybeans in Brazil, and of saffron in India. Forest intensification in Greece and Poland.
ML/CNN	- Soil data cube. - Data extraction from Sentinel-2 images. - Data processing and modelling using ground reflectance and heuristic bands. - Soil modelling using RF, SVR, and CNN. - Model uncertainty with a prediction interval.	Soil monitoring for the agri-food sector.	Soil monitoring of pine lands in Morocco, crops of fodder grasses in Lithuania, and crops of vegetables, strawberries, wheat, and alfalfa for Egypt.
ML/ANN, YOLOv4	- Real-time object detection using YOLO. - Image localisation boxes using bounding box regression. - Confidence score to improve the precision of the prediction. - Model performance.	The detection of agricultural growth phases.	The mapping of maize and sugar beet crop growth stages in Spain, and of soy and sunflower in France.
ML/DL	- Obtaining images of crops remotely. - The classification of images by quality. - The estimation of crop yield with ML and DL.	Crop yield estimation.	The estimation of horticultural production in the USA, maize in the Netherlands, and sugarcane and paddy in India.

References

1. El Hoummaidi, L.; Larabi, A.; Alam, K. Using Unmanned Aerial Systems and Deep Learning for Agriculture Mapping in Dubai. Heliyon; 2021; 7, e08154. [DOI: https://dx.doi.org/10.1016/j.heliyon.2021.e08154] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/34703924]

2. Dwivedi, A.K.; Singh, A.K.; Singh, D.; Kumar, H. Development of an Adaptive Linear Mixture Model for Decomposition of Mixed Pixels to Improve Crop Area Estimation Using Artificial Neural Network. IEEE Access; 2023; 11, pp. 5714-5723. [DOI: https://dx.doi.org/10.1109/ACCESS.2023.3236665]

3. Herrera-Franco, G.; Bollmann, H.A.; Pasqual Lofhagen, J.C.; Bravo-Montero, L.; Carrión-Mero, P. Approach on Water-Energy-Food (WEF) Nexus and Climate Change: A Tool in Decision-Making Processes. Environ. Dev.; 2023; 46, 100858. [DOI: https://dx.doi.org/10.1016/j.envdev.2023.100858]

4. Ahmad, K.; Abdelrazek, M.; Arora, C.; Bano, M.; Grundy, J. Requirements Engineering for Artificial Intelligence Systems: A Systematic Mapping Study. Inf. Softw. Technol.; 2023; 158, 107176. [DOI: https://dx.doi.org/10.1016/j.infsof.2023.107176]

5. Jong, S.C.; Ong, D.E.L.; Oh, E. State-of-the-Art Review of Geotechnical-Driven Artificial Intelligence Techniques in Underground Soil-Structure Interaction. Tunn. Undergr. Space Technol.; 2021; 113, 103946. [DOI: https://dx.doi.org/10.1016/j.tust.2021.103946]

6. Song, Y.; Kalacska, M.; Gašparović, M.; Yao, J.; Najibi, N. Advances in Geocomputation and Geospatial Artificial Intelligence (GeoAI) for Mapping. Int. J. Appl. Earth Obs. Geoinf.; 2023; 120, 103300. [DOI: https://dx.doi.org/10.1016/j.jag.2023.103300]

7. Herrera-Franco, G.; Escandón-Panchana, P.; Montalván, F.J.; Velastegui-Montoya, A. CLUE-S Model Based on GIS Applied to Management Strategies of Territory with Oil Wells—Case Study: Santa Elena, Ecuador. Geogr. Sustain.; 2022; 3, pp. 366-378. [DOI: https://dx.doi.org/10.1016/j.geosus.2022.11.001]

8. Priester, A.; Fan, R.E.; Shubert, J.; Rusu, M.; Vesal, S.; Shao, W.; Khandwala, Y.S.; Marks, L.S.; Natarajan, S.; Sonn, G.A. Prediction and Mapping of Intraprostatic Tumor Extent with Artificial Intelligence. Eur. Urol. Open Sci.; 2023; 54, pp. 20-27. [DOI: https://dx.doi.org/10.1016/j.euros.2023.05.018] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/37545845]

9. Rapinel, S.; Panhelleux, L.; Gayet, G.; Vanacker, R.; Lemercier, B.; Laroche, B.; Chambaud, F.; Guelmami, A.; Hubert-Moy, L. National Wetland Mapping Using Remote-Sensing-Derived Environmental Variables, Archive Field Data, and Artificial Intelligence. Heliyon; 2023; 9, e13482. [DOI: https://dx.doi.org/10.1016/j.heliyon.2023.e13482] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/36816231]

10. Kalai chelvi, T.; Gnanaprakasam, C.; Indumathy, M.; Khilar, R.; Sathish Kumar, P.J. Artificial Intelligence Based Optimization for Mapping IP Addresses to Prevent Cyber-Based Attacks. Meas. Sens.; 2022; 24, 100508. [DOI: https://dx.doi.org/10.1016/j.measen.2022.100508]

11. Jena, R.; Pradhan, B.; Gite, S.; Alamri, A.; Park, H.-J. A New Method to Promptly Evaluate Spatial Earthquake Probability Mapping Using an Explainable Artificial Intelligence (XAI) Model. Gondwana Res.; 2023; 123, pp. 54-67. [DOI: https://dx.doi.org/10.1016/j.gr.2022.10.003]

12. Karimidastenaei, Z.; Torabi Haghighi, A.; Rahmati, O.; Rasouli, K.; Rozbeh, S.; Pirnia, A.; Pradhan, B.; Kløve, B. Fog-Water Harvesting Capability Index (FCI) Mapping for a Semi-Humid Catchment Based on Socio-Environmental Variables and Using Artificial Intelligence Algorithms. Sci. Total Environ.; 2020; 708, 135115. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2019.135115] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/31787309]

13. Ghorbani, M.A.; Deo, R.C.; Kashani, M.H.; Shahabi, M.; Ghorbani, S. Artificial Intelligence-Based Fast and Efficient Hybrid Approach for Spatial Modelling of Soil Electrical Conductivity. Soil. Tillage Res.; 2019; 186, pp. 152-164. [DOI: https://dx.doi.org/10.1016/j.still.2018.09.012]

14. Silva, R.F.; Fava, M.C.; Saraiva, A.M.; Mendiondo, E.M.; Cugnasca, C.E.; Delbem, A.C.B. A Theoretical Framework for Multi-Hazard Risk Mapping on Agricultural Areas Considering Artificial Intelligence, IoT, and Climate Change Scenarios. Proceedings of the 13th EFITA International Conference; Online, 31 December 2021; 39.

15. Li, L.; Fan, Y.; Huang, X.; Tian, L. Real- Time UAV Weed Scout for Selective Weed Control by Adaptive Robust Control and Machine Learning Algorithm. Proceedings of the 2016 ASABE International Meeting; American Society of Agricultural and Biological Engineers; Orlando, FL, USA, 17 July 2016.

16. Arab, S.T.; Noguchi, R.; Matsushita, S.; Ahamed, T. Prediction of Grape Yields from Time-Series Vegetation Indices Using Satellite Remote Sensing and a Machine-Learning Approach. Remote Sens. Appl.; 2021; 22, 100485. [DOI: https://dx.doi.org/10.1016/j.rsase.2021.100485]

17. Rodrigues, L.; Magalhães, S.A.; da Silva, D.Q.; dos Santos, F.N.; Cunha, M. Computer Vision and Deep Learning as Tools for Leveraging Dynamic Phenological Classification in Vegetable Crops. Agronomy; 2023; 13, 463. [DOI: https://dx.doi.org/10.3390/agronomy13020463]

18. Pereira, A.G.; Porwol, L.; Ojo, A.; Curry, E. Towards a Temporal Deep Learning Model to Support Sustainable Agricultural Practices. In proceedings of CEUR Workshop. 2019; pp. 152-163. AICS Available online: http://dblp.uni-trier.de/db/conf/aics/aics2019.html#PereiraPOC19 (accessed on 15 May 2024).

19. Rangarajan, A.K.; Balu, E.J.; Boligala, M.S.; Jagannath, A.; Ranganathan, B.N. A Low-Cost UAV for Detection of Cercospora Leaf Spot in Okra Using Deep Convolutional Neural Network. Multimed. Tools Appl.; 2022; 81, pp. 21565-21589. [DOI: https://dx.doi.org/10.1007/s11042-022-12464-4]

20. Escandón-Panchana, P.; Herrera-Franco, G.; Martínez Cuevas, S.; Morante-Carballo, F. Prospects of UAVs in Agricultural Mapping. Proceedings of the International Conference on Applied Informatics; Guayaquil, Ecuador, 26–28 October 2023; pp. 309-322.

21. Reisi-Gahrouei, O.; Homayouni, S.; McNairn, H.; Hosseini, M.; Safari, A. Crop Biomass Estimation Using Multi Regression Analysis and Neural Networks from Multitemporal L-Band Polarimetric Synthetic Aperture Radar Data. Int. J. Remote Sens.; 2019; 40, pp. 6822-6840. [DOI: https://dx.doi.org/10.1080/01431161.2019.1594436]

22. Tsakiridis, N.L.; Samarinas, N.; Kalopesa, E.; Zalidis, G.C. Cognitive Soil Digital Twin for Monitoring the Soil Ecosystem: A Conceptual Framework. Soil. Syst.; 2023; 7, 88. [DOI: https://dx.doi.org/10.3390/soilsystems7040088]

23. Chatziantoniou, A.; Psomiadis, E.; Petropoulos, G. Co-Orbital Sentinel 1 and 2 for LULC Mapping with Emphasis on Wetlands in a Mediterranean Setting Based on Machine Learning. Remote Sens.; 2017; 9, 1259. [DOI: https://dx.doi.org/10.3390/rs9121259]

24. Ramírez-García, A.R.; Zavala-Cruz, J.; Rincón-Ramírez, J.A.; Guerrero-Peña, A.; García-López, E.; Sánchez-Hernández, R.; Castillo-Acosta, O.; Alfaro-Sánchez, G.; Ortiz-Pérez, M.A. Vegetation Cover and Land Use Change (1947–2019) in the Region of Los Ríos, Tabasco, México. Rev. Chapingo Ser. Cienc. For. y Del. Ambiente; 2022; 28, pp. 465-481. [DOI: https://dx.doi.org/10.5154/r.rchscfa.2022.01.001]

25. Fereidoon, M.; Koch, M. SWAT-MODSIM-PSO Optimization of Multi-Crop Planning in the Karkheh River Basin, Iran, under the Impacts of Climate Change. Sci. Total Environ.; 2018; 630, pp. 502-516. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2018.02.234] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/29486443]

26. Andrieu, N.; Dumas, P.; Hemmerlé, E.; Caforio, F.; Falconnier, G.N.; Blanchard, M.; Vayssières, J. Ex Ante Mapping of Favorable Zones for Uptake of Climate-Smart Agricultural Practices: A Case Study in West Africa. Environ. Dev.; 2021; 37, 100566. [DOI: https://dx.doi.org/10.1016/j.envdev.2020.100566]

27. Beloev, I.; Kinaneva, D.; Georgiev, G.; Hristov, G.; Zahariev, P. Artificial Intelligence-Driven Autonomous Robot for Precision Agriculture. Acta Technol. Agric.; 2021; 24, pp. 48-54. [DOI: https://dx.doi.org/10.2478/ata-2021-0008]

28. Syifa, M.; Park, S.J.; Achmad, A.R.; Lee, C.-W.; Eom, J. Flood Mapping Using Remote Sensing Imagery and Artificial Intelligence Techniques: A Case Study in Brumadinho, Brazil. J. Coast. Res.; 2019; 90, 197. [DOI: https://dx.doi.org/10.2112/SI90-024.1]

29. Saraiva, M.; Protas, É.; Salgado, M.; Souza, C. Automatic Mapping of Center Pivot Irrigation Systems from Satellite Images Using Deep Learning. Remote Sens.; 2020; 12, 558. [DOI: https://dx.doi.org/10.3390/rs12030558]

30. Dong, W.; Wu, T.; Sun, Y.; Luo, J. Digital Mapping of Soil Available Phosphorus Supported by AI Technology for Precision Agriculture. Proceedings of the 2018 7th International Conference on Agro-Geoinformatics (Agro-Geoinformatics); Hangzhou, China, 6–9 August 2018; pp. 1-5.

31. Sun, Z.; Di, L.; Fang, H.; Burgess, A. Deep Learning Classification for Crop Types in North Dakota. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.; 2020; 13, pp. 2200-2213. [DOI: https://dx.doi.org/10.1109/JSTARS.2020.2990104]

32. Rahmati, O.; Falah, F.; Dayal, K.S.; Deo, R.C.; Mohammadi, F.; Biggs, T.; Moghaddam, D.D.; Naghibi, S.A.; Bui, D.T. Machine Learning Approaches for Spatial Modeling of Agricultural Droughts in the South-East Region of Queensland Australia. Sci. Total Environ.; 2020; 699, 134230. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2019.134230] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/31522053]

33. López-Andreu, F.J.; Erena, M.; Dominguez-Gómez, J.A.; López-Morales, J.A. Sentinel-2 Images and Machine Learning as Tool for Monitoring of the Common Agricultural Policy: Calasparra Rice as a Case Study. Agronomy; 2021; 11, 621. [DOI: https://dx.doi.org/10.3390/agronomy11040621]

34. Herrera-Franco, G.; Sánchez-Arizo, V.; Escandón-Panchana, P.; Caicedo-Potosí, J.; Jaya-Montalvo, M.; Zambrano-Mendoza, J. Analysis of Scientific Contributions to Agricultural Development and Food Security in Ecuador. Int. J. Des. Nat. Ecodynamics; 2023; 18, pp. 1129-1139. [DOI: https://dx.doi.org/10.18280/ijdne.180514]

35. Rosle, R.; Che’Ya, N.N.; Ang, Y.; Rahmat, F.; Wayayok, A.; Berahim, Z.; Fazlil Ilahi, W.F.; Ismail, M.R.; Omar, M.H. Weed Detection in Rice Fields Using Remote Sensing Technique: A Review. Appl. Sci.; 2021; 11, 10701. [DOI: https://dx.doi.org/10.3390/app112210701]

36. Niknejad, N.; Ismail, W.; Bahari, M.; Hendradi, R.; Salleh, A.Z. Mapping the Research Trends on Blockchain Technology in Food and Agriculture Industry: A Bibliometric Analysis. Environ. Technol. Innov.; 2021; 21, 101272. [DOI: https://dx.doi.org/10.1016/j.eti.2020.101272]

37. Bertoglio, R.; Corbo, C.; Renga, F.M.; Matteucci, M. The Digital Agricultural Revolution: A Bibliometric Analysis Literature Review. IEEE Access; 2021; 9, pp. 134762-134782. [DOI: https://dx.doi.org/10.1109/ACCESS.2021.3115258]

38. Doussoulin, J.P.; Mougenot, B. Mapping Mining and Ecological Distribution Conflicts in Latin America, a Bibliometric Analysis. Resour. Policy; 2022; 77, 102650. [DOI: https://dx.doi.org/10.1016/j.resourpol.2022.102650]

39. Concari, A.; Kok, G.; Martens, P. Recycling Behaviour: Mapping Knowledge Domain through Bibliometrics and Text Mining. J. Environ. Manag.; 2022; 303, 114160. [DOI: https://dx.doi.org/10.1016/j.jenvman.2021.114160] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/34906834]

40. Escandón-Panchana, P.; Herrera-Franco, G.; Jaya-Montalvo, M.; Martínez-Cuevas, S. Geomatic Tools Used in the Management of Agricultural Activities: A Systematic Review. Environ. Dev. Sustain.; 2024; [DOI: https://dx.doi.org/10.1007/s10668-024-04576-8]

41. Singh, A.; Kumar, S. Picture Fuzzy Set and Quality Function Deployment Approach Based Novel Framework for Multi-Criteria Group Decision Making Method. Eng. Appl. Artif. Intell.; 2021; 104, 104395. [DOI: https://dx.doi.org/10.1016/j.engappai.2021.104395]

42. Bestelmeyer, B.T.; Marcillo, G.; McCord, S.E.; Mirsky, S.; Moglen, G.; Neven, L.G.; Peters, D.; Sohoulande, C.; Wakie, T. Scaling Up Agricultural Research with Artificial Intelligence. IT Prof.; 2020; 22, pp. 33-38. [DOI: https://dx.doi.org/10.1109/MITP.2020.2986062]

43. Dakir, A.; Barramou, F.; Alami, O.B. Towards a Machine Learning-Based Model for Automated Crop Type Mapping. Int. J. Adv. Comput. Sci. Appl.; 2023; 14, pp. 772-779. [DOI: https://dx.doi.org/10.14569/IJACSA.2023.0140185]

44. Posadas, B.B.; Ogunyiola, A.; Niewolny, K. Socially Responsible AI Assurance in Precision Agriculture for Farmers and Policymakers. AI Assurance; Elsevier: Amsterdam, The Netherlands, 2023; pp. 473-499.

45. Peña, J.; Gutiérrez, P.; Hervás-Martínez, C.; Six, J.; Plant, R.; López-Granados, F. Object-Based Image Classification of Summer Crops with Machine Learning Methods. Remote Sens.; 2014; 6, pp. 5019-5041. [DOI: https://dx.doi.org/10.3390/rs6065019]

46. Costa, L.; Kunwar, S.; Ampatzidis, Y.; Albrecht, U. Determining Leaf Nutrient Concentrations in Citrus Trees Using UAV Imagery and Machine Learning. Precis. Agric.; 2022; 23, pp. 854-875. [DOI: https://dx.doi.org/10.1007/s11119-021-09864-1]

47. Wang, S.; Azzari, G.; Lobell, D.B. Crop Type Mapping without Field-Level Labels: Random Forest Transfer and Unsupervised Clustering Techniques. Remote Sens. Environ.; 2019; 222, pp. 303-317. [DOI: https://dx.doi.org/10.1016/j.rse.2018.12.026]

48. Partel, V.; Charan Kakarla, S.; Ampatzidis, Y. Development and Evaluation of a Low-Cost and Smart Technology for Precision Weed Management Utilizing Artificial Intelligence. Comput. Electron. Agric.; 2019; 157, pp. 339-350. [DOI: https://dx.doi.org/10.1016/j.compag.2018.12.048]

49. Niazmardi, S.; Homayouni, S.; Safari, A. A Computationally Efficient Multi-Domain Active Learning Method for Crop Mapping Using Satellite Image Time-Series. Int. J. Remote Sens.; 2019; 40, pp. 6383-6394. [DOI: https://dx.doi.org/10.1080/01431161.2019.1591648]

50. Pashanejad, E.; Thierry, H.; Robinson, B.E.; Parrott, L. The Application of Semantic Modelling to Map Pollination Service Provisioning at Large Landscape Scales. Ecol. Model.; 2023; 484, 110452. [DOI: https://dx.doi.org/10.1016/j.ecolmodel.2023.110452]

51. Gutiérrez, P.A.; López-Granados, F.; Peña-Barragán, J.M.; Jurado-Expósito, M.; Hervás-Martínez, C. Logistic Regression Product-Unit Neural Networks for Mapping Ridolfia Segetum Infestations in Sunflower Crop Using Multitemporal Remote Sensed Data. Comput. Electron. Agric.; 2008; 64, pp. 293-306. [DOI: https://dx.doi.org/10.1016/j.compag.2008.06.001]

52. Arbelo, M.; Marchetti, F.; Hernandez-Leal, P.A.; Alonso-Benito, A.; Moreno-Ruiz, J.A. Multitemporal WorldView Satellites Imagery for Mapping Chestnut Trees. Proceedings of the Remote Sensing for Agriculture, Ecosystems, and Hydrology XIX, Warsaw, Poland, 2 November 2017; Neale, C.M.; Maltese, A. SPIE: Bellingham, WA, USA, 2017; 67.

53. Cortinas, E.; Emmi, L.; Gonzalez-de-Santos, P. Crop Identification and Growth Stage Determination for Autonomous Navigation of Agricultural Robots. Agronomy; 2023; 13, 2873. [DOI: https://dx.doi.org/10.3390/agronomy13122873]

54. Pascual-Venteo, A.B.; Portalés, E.; Berger, K.; Tagliabue, G.; Garcia, J.L.; Pérez-Suay, A.; Rivera-Caicedo, J.P.; Verrelst, J. Prototyping Crop Traits Retrieval Models for CHIME: Dimensionality Reduction Strategies Applied to PRISMA Data. Remote Sens.; 2022; 14, 2448. [DOI: https://dx.doi.org/10.3390/rs14102448] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/36017157]

55. Manfron, G.; Crema, A.; Boschetti, M.; Confalonieri, R. Testing Automatic Procedures to Map Rice Area and Detect Phenological Crop Information Exploiting Time Series Analysis of Remote Sensed MODIS Data. Proceedings of the Remote Sensing for Agriculture, Ecosystems, and Hydrology; Edinburgh, UK, 19 October 2012; Neale, C.M.U.; Maltese, A. 85311E.

56. Grieco, M.; Schmidt, M.; Warnemünde, S.; Backhaus, A.; Klück, H.-C.; Garibay, A.; Tandrón Moya, Y.A.; Jozefowicz, A.M.; Mock, H.-P.; Seiffert, U. et al. Dynamics and Genetic Regulation of Leaf Nutrient Concentration in Barley Based on Hyperspectral Imaging and Machine Learning. Plant Sci.; 2022; 315, 111123. [DOI: https://dx.doi.org/10.1016/j.plantsci.2021.111123]

57. Berger, K.; Hank, T.; Halabuk, A.; Rivera-Caicedo, J.P.; Wocher, M.; Mojses, M.; Gerhátová, K.; Tagliabue, G.; Dolz, M.M.; Venteo, A.B.P. et al. Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery. Remote Sens.; 2021; 13, 4711. [DOI: https://dx.doi.org/10.3390/rs13224711]

58. Mignolet, C.; Schott, C.; Benoît, M. Spatial Dynamics of Agricultural Practices on a Basin Territory: A Retrospective Study to Implement Models Simulating Nitrate Flow. The Case of the Seine Basin. Agronomie; 2004; 24, pp. 219-236. [DOI: https://dx.doi.org/10.1051/agro:2004015]

59. Osman, J.; Inglada, J.; Dejoux, J.-F. Assessment of a Markov Logic Model of Crop Rotations for Early Crop Mapping. Comput. Electron. Agric.; 2015; 113, pp. 234-243. [DOI: https://dx.doi.org/10.1016/j.compag.2015.02.015]

60. Kerkech, M.; Hafiane, A.; Canals, R. VddNet: Vine Disease Detection Network Based on Multispectral Images and Depth Map. Remote Sens.; 2020; 12, 3305. [DOI: https://dx.doi.org/10.3390/rs12203305]

61. László, I.; Csonka, B.; Bognár, E.; Csornai, G.; Lelkes, M.; László Martinovich, D.; Winkler, P.; Tikász, L.; Kocsis, A.; Mikus, G. Implementation and Control of the Good Agricultural and Environmental Conditions within the CwRS Programme in Hungary. Proceedings of the 25th EARSeL Symposium, 2005; Porto, Portugal, 6–11 June 2005; pp. 407-412.

62. Tulczyjew, L.; Kawulok, M.; Longepe, N.; Le Saux, B.; Nalepa, J. Graph Neural Networks Extract High-Resolution Cultivated Land Maps From Sentinel-2 Image Series. IEEE Geosci. Remote Sens. Lett.; 2022; 19, pp. 1-5. [DOI: https://dx.doi.org/10.1109/LGRS.2022.3185407]

63. Hawryło, P.; Wężyk, P. Predicting Growing Stock Volume of Scots Pine Stands Using Sentinel-2 Satellite Imagery and Airborne Image-Derived Point Clouds. Forests; 2018; 9, 274. [DOI: https://dx.doi.org/10.3390/f9050274]

64. Kalfas, I.; De Ketelaere, B.; Bunkens, K.; Saeys, W. Towards Automatic Insect Monitoring on Witloof Chicory Fields Using Sticky Plate Image Analysis. Ecol. Inf.; 2023; 75, 102037. [DOI: https://dx.doi.org/10.1016/j.ecoinf.2023.102037] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/37397435]

65. Thudi, M.; Palakurthi, R.; Schnable, J.C.; Chitikineni, A.; Dreisigacker, S.; Mace, E.; Srivastava, R.K.; Satyavathi, C.T.; Odeny, D.; Tiwari, V.K. et al. Genomic Resources in Plant Breeding for Sustainable Agriculture. J. Plant Physiol.; 2021; 257, 153351. [DOI: https://dx.doi.org/10.1016/j.jplph.2020.153351] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/33412425]

66. Nikaein, T.; Lopez-Dekker, P.; Steele-Dunne, S.C.; Kumar, V.; Huber, M. Modeling SAR Observables by Combining a Crop-Growth Model with Machine Learning. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.; 2023; 16, pp. 7763-7776. [DOI: https://dx.doi.org/10.1109/JSTARS.2023.3301124]

67. Selea, T. AgriSen-COG, a Multicountry, Multitemporal Large-Scale Sentinel-2 Benchmark Dataset for Crop Mapping Using Deep Learning. Remote Sens.; 2023; 15, 2980. [DOI: https://dx.doi.org/10.3390/rs15122980]

68. Veeck, G. Delineating Historical and Contemporary Agricultural Production Regions for China. Int. J. Cartogr.; 2022; 8, pp. 185-207. [DOI: https://dx.doi.org/10.1080/23729333.2021.1925495]

69. Bian, Y.; Li, L.; Jing, W. CACPU-Net: Channel Attention U-Net Constrained by Point Features for Crop Type Mapping. Front. Plant Sci.; 2023; 13, 1030595. [DOI: https://dx.doi.org/10.3389/fpls.2022.1030595]

70. Zhang, Y.; Wang, H.; Xu, R.; Yang, X.; Wang, Y.; Liu, Y. High-Precision Seedling Detection Model Based on Multi-Activation Layer and Depth-Separable Convolution Using Images Acquired by Drones. Drones; 2022; 6, 152. [DOI: https://dx.doi.org/10.3390/drones6060152]

71. Zheng, B.; Sun, G.; Meng, Z.; Nan, R. Vegetable Size Measurement Based on Stereo Camera and Keypoints Detection. Sensors; 2022; 22, 1617. [DOI: https://dx.doi.org/10.3390/s22041617] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/35214518]

72. Yang, H.; Gao, L.; Tang, N.; Yang, P. Experimental Analysis and Evaluation of Wide Residual Networks Based Agricultural Disease Identification in Smart Agriculture System. EURASIP J. Wirel. Commun. Netw.; 2019; 2019, 292. [DOI: https://dx.doi.org/10.1186/s13638-019-1613-z]

73. Zhang, P.; Li, D. EPSA-YOLO-V5s: A Novel Method for Detecting the Survival Rate of Rapeseed in a Plant Factory Based on Multiple Guarantee Mechanisms. Comput. Electron. Agric.; 2022; 193, 106714. [DOI: https://dx.doi.org/10.1016/j.compag.2022.106714]

74. Godara, S.; Toshniwal, D.; Parsad, R.; Bana, R.S.; Singh, D.; Bedi, J.; Jhajhria, A.; Dabas, J.P.S.; Marwaha, S. AgriMine: A Deep Learning Integrated Spatio-Temporal Analytics Framework for Diagnosing Nationwide Agricultural Issues Using Farmers’ Helpline Data. Comput. Electron. Agric.; 2022; 201, 107308. [DOI: https://dx.doi.org/10.1016/j.compag.2022.107308]

75. Randhawa, S.; Padmanaban, M.; Devi, U. Scope, Extent, and Challenges of an Automated Global Crop Classification Model. Proceedings of the IGARSS 2020—2020 IEEE International Geoscience and Remote Sensing Symposium; Waikoloa, HI, USA, 26 September 2020; pp. 4657-4660.

76. Pranuthi, G.; Srikanth, R. Globally Scalable and Locally Adaptable Solutions for Agriculture; Springer: Singapore, 2023; Volume 121, pp. 89-108.

77. Singh, K.K. An Artificial Intelligence and Cloud Based Collaborative Platform for Plant Disease Identification, Tracking and Forecasting for Farmers. Proceedings of the 2018 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM); Bangalore, India, 23–24 November 2018; pp. 49-56.

78. Kounte, M.R.; Hegde, P.S.; Dandur, N.R. Drone-Based Detection and Geo-Mapping of Wastes, Weeds and Diseases in Plants Using Deep Learning. Proceedings of the 2022 2nd Asian Conference on Innovation in Technology (ASIANCON); Pune, India, 26 August 2022; pp. 1-8.

79. Sumithra, C.V.; Manjula, T.R. An Extensive Study on Satellite Images of Sentinel 2 for Crop Type Identification. Proceedings of the 2023 International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems (ICAECIS); Bangalore, India, 19 April 2023; pp. 668-675.

80. Sonobe, R.; Tani, H.; Wang, X.; Kobayashi, N.; Shimamura, H. Discrimination of Crop Types with TerraSAR-X-Derived Information. Phys. Chem. Earth Parts A/B/C; 2015; 83–84, pp. 2-13. [DOI: https://dx.doi.org/10.1016/j.pce.2014.11.001]

81. Hosseiny, B.; Rastiveis, H.; Homayouni, S. An Automated Framework for Plant Detection Based on Deep Simulated Learning from Drone Imagery. Remote Sens.; 2020; 12, 3521. [DOI: https://dx.doi.org/10.3390/rs12213521]

82. Chen, L.-B.; Huang, X.-R.; Chen, W.-H. Design and Implementation of an Artificial Intelligence of Things-Based Autonomous Mobile Robot System for Pitaya Harvesting. IEEE Sens. J.; 2023; 23, pp. 13220-13235. [DOI: https://dx.doi.org/10.1109/JSEN.2023.3270844]

83. Ghazali, M.H.M.; Azmin, A.; Rahiman, W. Drone Implementation in Precision Agriculture—A Survey. Int. J. Emerg. Technol. Adv. Eng.; 2022; 12, pp. 67-77. [DOI: https://dx.doi.org/10.46338/ijetae0422_10]

84. Lee, D.-H.; Kim, H.-J.; Park, J.-H. UAV, a Farm Map, and Machine Learning Technology Convergence Classification Method of a Corn Cultivation Area. Agronomy; 2021; 11, 1554. [DOI: https://dx.doi.org/10.3390/agronomy11081554]

85. Ilyas, T.; Lee, J.; Won, O.; Jeong, Y.; Kim, H. Overcoming Field Variability: Unsupervised Domain Adaptation for Enhanced Crop-Weed Recognition in Diverse Farmlands. Front. Plant Sci.; 2023; 14, pp. 1-14. [DOI: https://dx.doi.org/10.3389/fpls.2023.1234616]

86. Morlin Carneiro, F.; Freire de Oliveira, M.; Luns Hatum de Almeida, S.; Lopes de Brito Filho, A.; Angeli Furlani, C.E.; De Souza Rolim, G.; Ferraudo, A.S.; Pereira da Silva, R. Biophysical Characteristics of Soybean Estimated by Remote Sensing Associated with Artificial Intelligence. Biosci. J.; 2022; 38, e38024. [DOI: https://dx.doi.org/10.14393/BJ-v38n0a2022-55925]

87. Resende, R.T.; Kuki, K.N.; Corrêa, T.R.; Zaidan, Ú.R.; Mota, P.H.S.; Telles, L.A.A.; Gonzales, D.G.E.; Motoike, S.Y.; Resende, M.D.V.; Leite, H.G. et al. Data-Based Agroecological Zoning of Acrocomia Aculeata: GIS Modeling and Ecophysiological Aspects into a Brazilian Representative Occurrence Area. Ind. Crops Prod.; 2020; 154, 112749. [DOI: https://dx.doi.org/10.1016/j.indcrop.2020.112749]

88. Bolfe, É.L.; Parreiras, T.C.; Silva, L.A.P.d.; Sano, E.E.; Bettiol, G.M.; Victoria, D.d.C.; Sanches, I.D.; Vicente, L.E. Mapping Agricultural Intensification in the Brazilian Savanna: A Machine Learning Approach Using Harmonized Data from Landsat Sentinel-2. ISPRS Int. J. Geoinf.; 2023; 12, 263. [DOI: https://dx.doi.org/10.3390/ijgi12070263]

89. Bordin, F.; Teixeira, E.C.; Rolim, S.B.A.; Tognoli, F.M.W.; Veronez, M.R.; Junior, L.G.d.S.; de Souza, C.F.N. Methodology for Acquisition of Intensity Data in Forest Targets Using Terrestrial Laser Scanner. IERI Procedia; 2013; 5, pp. 238-244. [DOI: https://dx.doi.org/10.1016/j.ieri.2013.11.098]

90. Bhadra, S.; Sagan, V.; Skobalski, J.; Grignola, F.; Sarkar, S.; Vilbig, J. End-to-End 3D CNN for Plot-Scale Soybean Yield Prediction Using Multitemporal UAV-Based RGB Images. Precis. Agric.; 2024; 25, pp. 834-864. [DOI: https://dx.doi.org/10.1007/s11119-023-10096-8]

91. Inglada, J.; Arias, M.; Tardy, B.; Hagolle, O.; Valero, S.; Morin, D.; Dedieu, G.; Sepulcre, G.; Bontemps, S.; Defourny, P. et al. Assessment of an Operational System for Crop Type Map Production Using High Temporal and Spatial Resolution Satellite Optical Imagery. Remote Sens.; 2015; 7, pp. 12356-12379. [DOI: https://dx.doi.org/10.3390/rs70912356]

92. Defourny, P.; Bontemps, S.; Bellemans, N.; Cara, C.; Dedieu, G.; Guzzonato, E.; Hagolle, O.; Inglada, J.; Nicola, L.; Rabaute, T. et al. Near Real-Time Agriculture Monitoring at National Scale at Parcel Resolution: Performance Assessment of the Sen2-Agri Automated System in Various Cropping Systems around the World. Remote Sens. Environ.; 2019; 221, pp. 551-568. [DOI: https://dx.doi.org/10.1016/j.rse.2018.11.007]

93. Gilbertson, J.K.; Kemp, J.; van Niekerk, A. Effect of Pan-Sharpening Multi-Temporal Landsat 8 Imagery for Crop Type Differentiation Using Different Classification Techniques. Comput. Electron. Agric.; 2017; 134, pp. 151-159. [DOI: https://dx.doi.org/10.1016/j.compag.2016.12.006]

94. Dutta, R.; Smith, D.; Rawnsley, R.; Bishop-Hurley, G.; Hills, J.; Timms, G.; Henry, D. Dynamic Cattle Behavioural Classification Using Supervised Ensemble Classifiers. Comput. Electron. Agric.; 2015; 111, pp. 18-28. [DOI: https://dx.doi.org/10.1016/j.compag.2014.12.002]

95. Amrani, A.; Sohel, F.; Diepeveen, D.; Murray, D.; Jones, M.G.K. Deep Learning-Based Detection of Aphid Colonies on Plants from a Reconstructed Brassica Image Dataset. Comput. Electron. Agric.; 2023; 205, 107587. [DOI: https://dx.doi.org/10.1016/j.compag.2022.107587]

96. Costello, B.; Osunkoya, O.O.; Sandino, J.; Marinic, W.; Trotter, P.; Shi, B.; Gonzalez, F.; Dhileepan, K. Detection of Parthenium Weed (Parthenium hysterophorus L.) and Its Growth Stages Using Artificial Intelligence. Agriculture; 2022; 12, 1838. [DOI: https://dx.doi.org/10.3390/agriculture12111838]

97. García, A.; Porwol, L.; Ojo, A.; Curry, E. Exploiting the Temporal Dimension of Remotely Sensed Imagery with Deep Learning Models. Proceedings of the 54th Hawaii International Conference on System Sciences; University of Hawai’i at Manoa; Kauai, HI, USA, 5 January 2021; pp. 5317-5326.

98. Zhang, C.; Di, L.; Lin, L.; Zhao, H.; Li, H.; Yang, A.; Guo, L.; Yang, Z. Cyberinformatics Tool for In-Season Crop-Specific Land Cover Monitoring: Design, Implementation, and Applications of ICrop. Comput. Electron. Agric.; 2023; 213, 108199. [DOI: https://dx.doi.org/10.1016/j.compag.2023.108199]

99. Filippi, A.M.; Archibald, R.; Bhaduri, B.L.; Bright, E.A. Hyperspectral Agricultural Mapping Using Support Vector Machine-Based Endmember Extraction (SVM-BEE). Opt. Express; 2009; 17, 23823. [DOI: https://dx.doi.org/10.1364/OE.17.023823] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/20052093]

100. Rodríguez-Aguilera, A.I.; Domingo-Santos, J. Cartography and Landscape of Agrarian Colonisation Villages in Spain during the 20th Century: Graphic Recording and Reconstruction of the Productive Territory, the Case of El Chaparral (Granada). Sustainability; 2022; 14, 4324. [DOI: https://dx.doi.org/10.3390/su14074324]

101. Aguilar, F.J.; Carvajal, F.; Aguilar, M.A.; Agüera, F. Developing Digital Cartography in Rural Planning Applications. Comput. Electron. Agric.; 2007; 55, pp. 89-106. [DOI: https://dx.doi.org/10.1016/j.compag.2006.12.008]

102. Gonzalez-Alonso, F.; Casonova Roque, J.L. Forest Cartography of Spain Based on the Classification of NOAA-AVHRR Multitemporal Images. Proceedings of the IGARSS’97. 1997 IEEE International Geoscience and Remote Sensing Symposium Proceedings. Remote Sensing—A Scientific Vision for Sustainable Development; Singapore, 3–8 August 1997; pp. 87-88.

103. Serra, P.; Moré, G.; Pons, X. Thematic Accuracy Consequences in Cadastre Land-Cover Enrichment from a Pixel and from a Polygon Perspective. Photogramm. Eng. Remote Sens.; 2009; 75, pp. 1441-1449. [DOI: https://dx.doi.org/10.14358/PERS.75.12.1441]

104. Ghadban, S.; Ameztegui, A.; Rodrigues, M.; Chocarro, C.; Alcasena, F.; Vega-Garcia, C. Stand Structure and Local Landscape Variables Are the Dominant Factors Explaining Shrub and Tree Diversity in Mediterranean Forests. Sustainability; 2021; 13, 11658. [DOI: https://dx.doi.org/10.3390/su132111658]

105. Cots-Folch, R.; Aitkenhead, M.J.; Martínez-Casasnovas, J.A. Mapping Land Cover from Detailed Aerial Photography Data Using Textural and Neural Network Analysis. Int. J. Remote Sens.; 2007; 28, pp. 1625-1642. [DOI: https://dx.doi.org/10.1080/01431160600887722]

106. Mauro, G. Agricultural Terraced Landscapes in the Province of Trieste (Northeastern Italy). Geocomputation, Sustainability and Environmental Planning; Springer: Berlin, Heidelberg, 2011; pp. 91-109.

107. Statuto, D.; Cillis, G.; Picuno, P. Historical Cartography and GIS Tools for the Analysis of Land Use and Landscape Changes; CORTA Lab: Opatija, Croatia, 2015.

108. Helmholz, P.; Rottensteiner, F.; Heipke, C. Semi-Automatic Verification of Cropland and Grassland Using Very High Resolution Mono-Temporal Satellite Images. ISPRS J. Photogramm. Remote Sens.; 2014; 97, pp. 204-218. [DOI: https://dx.doi.org/10.1016/j.isprsjprs.2014.09.008]

109. Le Ber, F. A Prototype Model-Based Expert System for Agricultural Landscape Analysis. AI Appl.-Nat. Resour. Agric. Environ. Sci.; 1995; 9, pp. 91-101.

110. Cochard, P.; Laurie, M.; Veyrand, B.; Le Bizec, B.; Poirot, B.; Marchand, P. PAH7 Concentration Reflects Anthropization: A Study Using Environmental Biomonitoring with Honeybees. Sci. Total Environ.; 2021; 751, 141831. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2020.141831]

111. Demetriou, D.; Stillwell, J.; Seel, L. LandSpaCES: A Spatial Expert System for Land Consolidation. Advancing geoinformation Science for a Changing World; Springer: Berlin/Heidelberg, Germany, 2011; pp. 249-274.

112. Roumenina, E.; Vassilev, V.; Ruskov, K. Large Scale Cartography and Analyses of Man-Induced Transformation in an Urban Area Using Satellite Imagery with Very High Resolution. Proceedings of the 2009 4th International Conference on Recent Advances in Space Technologies; Istanbul, Turkey, 11–13 June 2009; pp. 313-316.

113. Petropoulos, G.P.; Arvanitis, K.; Sigrimis, N.; Piromalis, D.D.; Boglou, A.K. Land Use Cartography from Hyperion Hyperspectral Imagery Analysis: Results from a Mediterranean Site. Proceedings of the 2012 IEEE 24th International Conference on Tools with Artificial Intelligence; Athens, Greece, 7–9 November 2012; pp. 26-31.

114. Osińska-Skotak, K.; Radecka, A.; Piórkowski, H.; Michalska-Hejduk, D.; Kopeć, D.; Tokarska-Guzik, B.; Ostrowski, W.; Kania, A.; Niedzielko, J. Mapping Succession in Non-Forest Habitats by Means of Remote Sensing: Is the Data Acquisition Time Critical for Species Discrimination?. Remote Sens.; 2019; 11, 2629. [DOI: https://dx.doi.org/10.3390/rs11222629]

115. Osmólska, A.; Hawryło, P. Using a GEOBIA Framework for Integrating Different Data Sources and Classification Methods in Context of Land Use/Land Cover Mapping. Geod. Cartogr. Pol. Acad. Sci.; 2018; 67, pp. 99-116. [DOI: https://dx.doi.org/10.24425/118699]

116. Schwieder, M.; Leitão, P.; Suess, S.; Senf, C.; Hostert, P. Estimating Fractional Shrub Cover Using Simulated EnMAP Data: A Comparison of Three Machine Learning Regression Techniques. Remote Sens.; 2014; 6, pp. 3427-3445. [DOI: https://dx.doi.org/10.3390/rs6043427]

117. O’Connell, J.; Bradter, U.; Benton, T.G. Wide-Area Mapping of Small-Scale Features in Agricultural Landscapes Using Airborne Remote Sensing. ISPRS J. Photogramm. Remote Sens.; 2015; 109, pp. 165-177. [DOI: https://dx.doi.org/10.1016/j.isprsjprs.2015.09.007] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/26664131]

118. Kononenko, O. Transformation of Land Relations Regulation Mechanism throughout the Rural Sustainable Development Context. Agric. Resour. Econ. Int. Sci. e-J.; 2019; 5, pp. 19-36. [DOI: https://dx.doi.org/10.51599/are.2019.05.01.02]

119. Raab, C.; Barrett, B.; Cawkwell, F.; Green, S. Evaluation of Multi-Temporal and Multi-Sensor Atmospheric Correction Strategies for Land-Cover Accounting and Monitoring in Ireland. Remote Sens. Lett.; 2015; 6, pp. 784-793. [DOI: https://dx.doi.org/10.1080/2150704X.2015.1076950]

120. Goksel, C.; Bektas, F.; Keskin, M.; Celik, B.; Cihan, C.; Yagmur, N. Evaluation of Classification Methods for Detection of Greenhouses from SPOT 5 Satellite Imagery. Proceedings of the 6th International Conference on Cartography and GIS; Albena, Bulgaria, 13–17 June 2016; Bandrova, K.M.T. pp. 712-717.

121. Li, X.; Chen, W.; Cheng, X.; Wang, L. A Comparison of Machine Learning Algorithms for Mapping of Complex Surface-Mined and Agricultural Landscapes Using ZiYuan-3 Stereo Satellite Imagery. Remote Sens.; 2016; 8, 514. [DOI: https://dx.doi.org/10.3390/rs8060514]

122. Chuang, Y.-C.; Shiu, Y.-S. A Comparative Analysis of Machine Learning with WorldView-2 Pan-Sharpened Imagery for Tea Crop Mapping. Sensors; 2016; 16, 594. [DOI: https://dx.doi.org/10.3390/s16050594]

123. Ortiz, A.; Negandhi, D.; Mysorekar, S.R.; Nagaraju, S.K.; Kiesecker, J.; Robinson, C.; Bhatia, P.; Khurana, A.; Wang, J.; Oviedo, F. et al. An Artificial Intelligence Dataset for Solar Energy Locations in India. Sci. Data; 2022; 9, 497. [DOI: https://dx.doi.org/10.1038/s41597-022-01499-9] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/35974002]

124. Singh, R.K.; Das, A.K.; Jain, H.; Singh, P.; Kumar, P. Mapping and Identification of Trees Using Semantic Segmentation Deep Learning Neural Network. Forest Dynamics and Conservation; Springer: Singapore, 2022; pp. 385-398.

125. Debats, S.R.; Luo, D.; Estes, L.D.; Fuchs, T.J.; Caylor, K.K. A Generalized Computer Vision Approach to Mapping Crop Fields in Heterogeneous Agricultural Landscapes. Remote Sens. Environ.; 2016; 179, pp. 210-221. [DOI: https://dx.doi.org/10.1016/j.rse.2016.03.010]

126. Kang, J.; Wang, J.; Zhong, M. Geographic and Cartographic Inconsistency Factors among Different Cropland Classification Datasets: A Field Validation Case in Cambodia. Open Geosci.; 2022; 14, pp. 966-984. [DOI: https://dx.doi.org/10.1515/geo-2022-0409]

127. Hassan, M.; Southworth, J. Analyzing Land Cover Change and Urban Growth Trajectories of the Mega-Urban Region of Dhaka Using Remotely Sensed Data and an Ensemble Classifier. Sustainability; 2017; 10, 10. [DOI: https://dx.doi.org/10.3390/su10010010]

128. Gharaibeh, A.; Shaamala, A.; Obeidat, R.; Al-Kofahi, S. Improving Land-Use Change Modeling by Integrating ANN with Cellular Automata-Markov Chain Model. Heliyon; 2020; 6, e05092. [DOI: https://dx.doi.org/10.1016/j.heliyon.2020.e05092] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/33024869]

129. Park, J.; Jang, S.; Hong, R.; Suh, K.; Song, I. Development of Land Cover Classification Model Using AI Based FusionNet Network. Remote Sens.; 2020; 12, 3171. [DOI: https://dx.doi.org/10.3390/rs12193171]

130. Hong, R.; Park, J.; Jang, S.; Shin, H.; Kim, H.; Song, I. Development of a Parcel-Level Land Boundary Extraction Algorithm for Aerial Imagery of Regularly Arranged Agricultural Areas. Remote Sens.; 2021; 13, 1167. [DOI: https://dx.doi.org/10.3390/rs13061167]

131. Silva Guimarães, U.; de Lourdes Bueno Trindade Galo, M.; da Silva Narvaes, I.; de Queiroz da Silva, A. Cosmo-SkyMed and TerraSAR-X Datasets for Geomorphological Mapping in the Eastern of Marajó Island, Amazon Coast. Geomorphology; 2020; 350, 106934. [DOI: https://dx.doi.org/10.1016/j.geomorph.2019.106934]

132. Rodríguez-Soto, C.; Velazquez, A.; Monroy-Vilchis, O.; Lemes, P.; Loyola, R. Joint Ecological, Geographical and Cultural Approach to Identify Territories of Opportunity for Large Vertebrates Conservation in Mexico. Biodivers. Conserv.; 2017; 26, pp. 1899-1918. [DOI: https://dx.doi.org/10.1007/s10531-017-1335-7]

133. Hernández-Moreno, M.M.; Téllez Valdés, O.; Martínez Meyer, E.; Islas-Saldaña, L.A.; Salazar-Rojas, V.M.; Macías-Cuéllar, H. Distribución de La Cobertura Vegetal y Del Uso Del Terreno Del Municipio de Zapotitlán, Puebla, México. Rev. Mex. Biodivers.; 2021; 92, 923649. [DOI: https://dx.doi.org/10.22201/ib.20078706e.2021.92.3649]

134. Abida, K.; Barbouchi, M.; Boudabbous, K.; Toukabri, W.; Saad, K.; Bousnina, H.; Sahli Chahed, T. Sentinel-2 Data for Land Use Mapping: Comparing Different Supervised Classifications in Semi-Arid Areas. Agriculture; 2022; 12, 1429. [DOI: https://dx.doi.org/10.3390/agriculture12091429]

135. Ben Slimene Ben Amor, I.; Chehata, N.; Bailly, J.-S.; Farah, I.R.; Lagacherie, P. Parcel-Based Active Learning for Large Extent Cultivated Area Mapping. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.; 2018; 11, pp. 79-88. [DOI: https://dx.doi.org/10.1109/JSTARS.2017.2751148]

136. Waldner, F.; Jacques, D.C.; Löw, F. The Impact of Training Class Proportions on Binary Cropland Classification. Remote Sens. Lett.; 2017; 8, pp. 1122-1131. [DOI: https://dx.doi.org/10.1080/2150704X.2017.1362124]

137. Teluguntla, P.; Thenkabail, P.S.; Oliphant, A.; Xiong, J.; Gumma, M.K.; Congalton, R.G.; Yadav, K.; Huete, A. A 30-m Landsat-Derived Cropland Extent Product of Australia and China Using Random Forest Machine Learning Algorithm on Google Earth Engine Cloud Computing Platform. ISPRS J. Photogramm. Remote Sens.; 2018; 144, pp. 325-340. [DOI: https://dx.doi.org/10.1016/j.isprsjprs.2018.07.017]

138. Graf, L.; Bach, H.; Tiede, D. Semantic Segmentation of Sentinel-2 Imagery for Mapping Irrigation Center Pivots. Remote Sens.; 2020; 12, 3937. [DOI: https://dx.doi.org/10.3390/rs12233937]

139. Fienen, M.N.; Nolan, B.T.; Kauffman, L.J.; Feinstein, D.T. Metamodeling for Groundwater Age Forecasting in the Lake Michigan Basin. Water Resour. Res.; 2018; 54, pp. 4750-4766. [DOI: https://dx.doi.org/10.1029/2017WR022387]

140. Sharaf El Din, E.; Zhang, Y.; Suliman, A. Mapping Concentrations of Surface Water Quality Parameters Using a Novel Remote Sensing and Artificial Intelligence Framework. Int. J. Remote Sens.; 2017; 38, pp. 1023-1042. [DOI: https://dx.doi.org/10.1080/01431161.2016.1275056]

141. Das, R.; Saha, S. Spatial Mapping of Groundwater Potentiality Applying Ensemble of Computational Intelligence and Machine Learning Approaches. Groundw. Sustain. Dev.; 2022; 18, 100778. [DOI: https://dx.doi.org/10.1016/j.gsd.2022.100778]

142. Bordbar, M.; Busico, G.; Sirna, M.; Tedesco, D.; Mastrocicco, M. A Multi-Step Approach to Evaluate the Sustainable Use of Groundwater Resources for Human Consumption and Agriculture. J. Environ. Manag.; 2023; 347, 119041. [DOI: https://dx.doi.org/10.1016/j.jenvman.2023.119041]

143. Barroso, M.F.; Ramalhosa, M.J.; Olhero, A.; Antão, M.C.; Pina, M.F.; Guimarães, L.; Teixeira, J.; Afonso, M.J.; Delerue-Matos, C.; Chaminé, H.I. Assessment of Groundwater Contamination in an Agricultural Peri-Urban Area (NW Portugal): An Integrated Approach. Environ. Earth Sci.; 2015; 73, pp. 2881-2894. [DOI: https://dx.doi.org/10.1007/s12665-014-3297-3]

144. Møller, A.B.; Beucher, A.; Iversen, B.V.; Greve, M.H. Predicting Artificially Drained Areas by Means of a Selective Model Ensemble. Geoderma; 2018; 320, pp. 30-42. [DOI: https://dx.doi.org/10.1016/j.geoderma.2018.01.018]

145. Weikmann, G.; Marinelli, D.; Paris, C.; Migdall, S.; Gleisberg, E.; Appel, F.; Bach, H.; Dowling, J.; Bruzzone, L. Multiyear Mapping of Water Demand at Crop Level: An End-to-End Workflow Based on High-Resolution Crop Type Maps and Meteorological Data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.; 2023; 16, pp. 6758-6775. [DOI: https://dx.doi.org/10.1109/JSTARS.2023.3294107]

146. Taşan, S. Estimation of Groundwater Quality Using an Integration of Water Quality Index, Artificial Intelligence Methods and GIS: Case Study, Central Mediterranean Region of Turkey. Appl. Water Sci.; 2023; 13, 15. [DOI: https://dx.doi.org/10.1007/s13201-022-01810-4]

147. Alaboz, P.; Başkan, O.; Dengiz, O. Computational Intelligence Applied to the Least Limiting Water Range to Estimate Soil Water Content Using GIS and Geostatistical Approaches in Alluvial Lands^*. Irrig. Drain.; 2021; 70, pp. 1129-1144. [DOI: https://dx.doi.org/10.1002/ird.2628]

148. Sengorur, B.; Koklu, R.; Ates, A. Water Quality Assessment Using Artificial Intelligence Techniques: SOM and ANN—A Case Study of Melen River Turkey. Water Qual. Expo. Health; 2015; 7, pp. 469-490. [DOI: https://dx.doi.org/10.1007/s12403-015-0163-9]

149. Çinar, Ö.; Merdun, H. Application of an Unsupervised Artificial Neural Network Technique to Multivariant Surface Water Quality Data. Ecol. Res.; 2009; 24, pp. 163-173. [DOI: https://dx.doi.org/10.1007/s11284-008-0495-z]

150. Singh, M.; Tyagi, K.D. Detection of Expanded Reformed Geographical Area in Bi-Temporal Multispectral Satellite Images Using Machine Intelligence Neural Network. J. Indian. Soc. Remote Sens.; 2022; 50, pp. 623-633. [DOI: https://dx.doi.org/10.1007/s12524-021-01476-6]

151. Chang, F.-J.; Wang, Y.-C.; Tsai, W.-P. Modelling Intelligent Water Resources Allocation for Multi-Users. Water Resour. Manag.; 2016; 30, pp. 1395-1413. [DOI: https://dx.doi.org/10.1007/s11269-016-1229-6]

152. Na, X.D.; Zang, S.Y.; Wu, C.S.; Li, W.L. Mapping Forested Wetlands in the Great Zhan River Basin through Integrating Optical, Radar, and Topographical Data Classification Techniques. Environ. Monit. Assess.; 2015; 187, 696. [DOI: https://dx.doi.org/10.1007/s10661-015-4914-7]

153. Jain, S.K.; Das, A.; Srivastava, D.K. Application of ANN for Reservoir Inflow Prediction and Operation. J. Water Resour. Plan. Manag.; 1999; 125, pp. 263-271. [DOI: https://dx.doi.org/10.1061/(ASCE)0733-9496(1999)125:5(263)]

154. Zaresefat, M.; Derakhshani, R.; Nikpeyman, V.; GhasemiNejad, A.; Raoof, A. Using Artificial Intelligence to Identify Suitable Artificial Groundwater Recharge Areas for the Iranshahr Basin. Water; 2023; 15, 1182. [DOI: https://dx.doi.org/10.3390/w15061182]

155. Darabi, H.; Moradi, E.; Davudirad, A.A.; Ehteram, M.; Cerda, A.; Haghighi, A.T. Efficient Rainwater Harvesting Planning Using Socio-Environmental Variables and Data-Driven Geospatial Techniques. J. Clean. Prod.; 2021; 311, 127706. [DOI: https://dx.doi.org/10.1016/j.jclepro.2021.127706]

156. Nadiri, A.A.; Norouzi, H.; Khatibi, R.; Gharekhani, M. Groundwater DRASTIC Vulnerability Mapping by Unsupervised and Supervised Techniques Using a Modelling Strategy in Two Levels. J. Hydrol.; 2019; 574, pp. 744-759. [DOI: https://dx.doi.org/10.1016/j.jhydrol.2019.04.039]

157. Ansari, M.; Akhoondzadeh, M. Mapping Water Salinity Using Landsat-8 OLI Satellite Images (Case Study: Karun Basin Located in Iran). Adv. Space Res.; 2020; 65, pp. 1490-1502. [DOI: https://dx.doi.org/10.1016/j.asr.2019.12.007]

158. Khiavi, A.N.; Tavoosi, M.; Kuriqi, A. Conjunct Application of Machine Learning and Game Theory in Groundwater Quality Mapping. Environ. Earth Sci.; 2023; 82, 395. [DOI: https://dx.doi.org/10.1007/s12665-023-11059-y]

159. Harada, M.; Tominaga, T.; Hiramatsu, K.; Marui, A. Real-Time Prediction of Chlorophyll-A Time Series in a Eutrophic Agricultural Reservoir in a Coastal Zone Using Recurrent Neural Networks with Periodic Chaos Neurons. Irrig. Drain.; 2013; 62, pp. 36-43. [DOI: https://dx.doi.org/10.1002/ird.1757]

160. Phong, T.V.; Pham, B.T.; Trinh, P.T.; Ly, H.; Vu, Q.H.; Ho, L.S.; Le, H.V.; Phong, L.H.; Avand, M.; Prakash, I. Groundwater Potential Mapping Using GIS-Based Hybrid Artificial Intelligence Methods. Groundwater; 2021; 59, pp. 745-760. [DOI: https://dx.doi.org/10.1111/gwat.13094] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/33745148]

161. Yen, H.P.H.; Pham, B.T.; Phong, T.V.; Ha, D.H.; Costache, R.; Le, H.V.; Nguyen, H.D.; Amiri, M.; Tao, N.V.; Prakash, I. Locally Weighted Learning Based Hybrid Intelligence Models for Groundwater Potential Mapping and Modeling: A Case Study at Gia Lai Province, Vietnam. Geosci. Front.; 2021; 12, 101154. [DOI: https://dx.doi.org/10.1016/j.gsf.2021.101154]

162. Nawaz, N.; Harun, S.; Talei, A.; Chang, T.K. Event-Based Rainfall-Runoff Modeling Using Adaptive Network-Based Fuzzy Inference Sytem. J. Teknol.; 2016; 78, pp. 2180-3722.

163. Garcia-Molsosa, A.; Orengo, H.A.; Petrie, C.A. Reconstructing Long-Term Settlement Histories on Complex Alluvial Floodplains by Integrating Historical Map Analysis and Remote-Sensing: An Archaeological Analysis of the Landscape of the Indus River Basin. Herit. Sci.; 2023; 11, 141. [DOI: https://dx.doi.org/10.1186/s40494-023-00985-6]

164. Msaddek, M.H.; Moumni, Y.; Ayari, A.; El May, M.; Chenini, I. Artificial Intelligence Modelling Framework for Mapping Groundwater Vulnerability of Fractured Aquifer. Geocarto Int.; 2022; 37, pp. 10480-10510. [DOI: https://dx.doi.org/10.1080/10106049.2022.2037729]

165. Malerba, M.E.; Wright, N.; Macreadie, P.I. A Continental-Scale Assessment of Density, Size, Distribution and Historical Trends of Farm Dams Using Deep Learning Convolutional Neural Networks. Remote Sens.; 2021; 13, 319. [DOI: https://dx.doi.org/10.3390/rs13020319]

166. Lin, J.; Sreng, C.; Oare, E.; Batarseh, F.A. NeuralFlood: An AI-Driven Flood Susceptibility Index. Front. Water; 2023; 5, 1291305. [DOI: https://dx.doi.org/10.3389/frwa.2023.1291305]

167. Marín Puig, A.; Sainz de la Maza, M. Cartografia de La Inundabilitat Local al Delta Del Llobregat Durant El Temporal Gloria. Doc. Anal. Geogr.; 2023; 69, pp. 359-384. [DOI: https://dx.doi.org/10.5565/rev/dag.759]

168. Martínez-García, V.; Martínez-Paz, J.M.; Alcon, F. The Economic Value of Flood Risk Regulation by Agroecosystems at Semiarid Areas. Agric. Water Manag.; 2022; 266, 107565. [DOI: https://dx.doi.org/10.1016/j.agwat.2022.107565]

169. Samaniego, L.; Kumar, R.; Zink, M. Implications of Parameter Uncertainty on Soil Moisture Drought Analysis in Germany. J. Hydrometeorol.; 2013; 14, pp. 47-68. [DOI: https://dx.doi.org/10.1175/JHM-D-12-075.1]

170. Petropoulos, G.P.; Knorr, W.; Scholze, M.; Boschetti, L.; Karantounias, G. Combining ASTER Multispectral Imagery Analysis and Support Vector Machines for Rapid and Cost-Effective Post-Fire Assessment: A Case Study from the Greek Wildland Fires of 2007. Nat. Hazards Earth Syst. Sci.; 2010; 10, pp. 305-317. [DOI: https://dx.doi.org/10.5194/nhess-10-305-2010]

171. Plataridis, K.; Mallios, Z. Flood Susceptibility Mapping Using Hybrid Models Optimized with Artificial Bee Colony. J. Hydrol.; 2023; 624, 129961. [DOI: https://dx.doi.org/10.1016/j.jhydrol.2023.129961]

172. Doxani, G.; Siachalou, S.; Mitraka, Z.; Patias, P. Decision Making on Disaster Management in Agriculture with Sentinel Applications. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci.; 2019; XLII-3/W8, pp. 121-126. [DOI: https://dx.doi.org/10.5194/isprs-archives-XLII-3-W8-121-2019]

173. Milanović, S.; Kaczmarowski, J.; Ciesielski, M.; Trailović, Z.; Mielcarek, M.; Szczygieł, R.; Kwiatkowski, M.; Bałazy, R.; Zasada, M.; Milanović, S.D. Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods. Forests; 2022; 14, 46. [DOI: https://dx.doi.org/10.3390/f14010046]

174. Senel, G.; Eroglu, M.; Bektas Balcik, F.; Goksel Cand, C.; Student, M.; Filiz Bektas Balcik, A.; Goksel, C. Flood Extent Determination in Agricultural Fields Using Sentinel-2 Data and Random Forest Classification. Proceedings of the 8th International Conference on Cartography and GIS; Nessebar, Bulgaria, 2020.

175. Çubukçu, E.A.; Demir, v.; Sevimli, M.F. Modeling of Annual Maximum Flows with Geographic Data Components and Artificial Neural Networks. Int. J. Eng. Geosci.; 2023; 8, pp. 200-211. [DOI: https://dx.doi.org/10.26833/ijeg.1125412]

176. Aydin, H.E.; Iban, M.C. Predicting and Analyzing Flood Susceptibility Using Boosting-Based Ensemble Machine Learning Algorithms with SHapley Additive ExPlanations. Nat. Hazards; 2023; 116, pp. 2957-2991. [DOI: https://dx.doi.org/10.1007/s11069-022-05793-y]

177. Rahmati, O.; Falah, F.; Naghibi, S.A.; Biggs, T.; Soltani, M.; Deo, R.C.; Cerdà, A.; Mohammadi, F.; Tien Bui, D. Land Subsidence Modelling Using Tree-Based Machine Learning Algorithms. Sci. Total Environ.; 2019; 672, pp. 239-252. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2019.03.496]

178. Nadiri, A.A.; Taheri, Z.; Khatibi, R.; Barzegari, G.; Dideban, K. Introducing a New Framework for Mapping Subsidence Vulnerability Indices (SVIs): ALPRIFT. Sci. Total Environ.; 2018; 628–629, pp. 1043-1057. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2018.02.031] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/30045529]

179. Arabameri, A.; Saha, S.; Roy, J.; Tiefenbacher, J.P.; Cerda, A.; Biggs, T.; Pradhan, B.; Thi Ngo, P.T.; Collins, A.L. A Novel Ensemble Computational Intelligence Approach for the Spatial Prediction of Land Subsidence Susceptibility. Sci. Total Environ.; 2020; 726, 138595. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2020.138595] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/32320885]

180. Nhu, V.-H.; Janizadeh, S.; Avand, M.; Chen, W.; Farzin, M.; Omidvar, E.; Shirzadi, A.; Shahabi, H.; Clague, J.J.; Jaafari, A. et al. GIS-Based Gully Erosion Susceptibility Mapping: A Comparison of Computational Ensemble Data Mining Models. Appl. Sci.; 2020; 10, 2039. [DOI: https://dx.doi.org/10.3390/app10062039]

181. Salame, C.W.; Queiroz, J.C.B.; de Miranda Rocha, G.; Amin, M.M. Mapping the Risk of Burning in the Brazilian Amazon with the Use of Logistic Regression and Fuzzy Inference. Math. Geosci.; 2012; 44, pp. 241-256. [DOI: https://dx.doi.org/10.1007/s11004-012-9386-5]

182. Mohamed, E.S.; Jalhoum, M.E.M.; Belal, A.A.; Hendawy, E.; Azab, Y.F.A.; Kucher, D.E.; Shokr, M.S.; El Behairy, R.A.; El Arwash, H.M. A Novel Approach for Predicting Heavy Metal Contamination Based on Adaptive Neuro-Fuzzy Inference System and GIS in an Arid Ecosystem. Agronomy; 2023; 13, 1873. [DOI: https://dx.doi.org/10.3390/agronomy13071873]

183. Aouragh, M.H.; Ijlil, S.; Essahlaoui, N.; Essahlaoui, A.; El Hmaidi, A.; El Ouali, A.; Mridekh, A. Remote Sensing and GIS-Based Machine Learning Models for Spatial Gully Erosion Prediction: A Case Study of Rdat Watershed in Sebou Basin, Morocco. Remote Sens. Appl.; 2023; 30, 100939. [DOI: https://dx.doi.org/10.1016/j.rsase.2023.100939]

184. Orimoloye, I.R.; Olusola, A.O.; Belle, J.A.; Pande, C.B.; Ololade, O.O. Drought Disaster Monitoring and Land Use Dynamics: Identification of Drought Drivers Using Regression-Based Algorithms. Nat. Hazards; 2022; 112, pp. 1085-1106. [DOI: https://dx.doi.org/10.1007/s11069-022-05219-9]

185. Dutta, R.; Morshed, A.; Aryal, J.; D’Este, C.; Das, A. Development of an Intelligent Environmental Knowledge System for Sustainable Agricultural Decision Support. Environ. Model. Softw.; 2014; 52, pp. 264-272. [DOI: https://dx.doi.org/10.1016/j.envsoft.2013.10.004]

186. Teng, H.; Viscarra Rossel, R.A.; Shi, Z.; Behrens, T.; Chappell, A.; Bui, E. Assimilating Satellite Imagery and Visible–near Infrared Spectroscopy to Model and Map Soil Loss by Water Erosion in Australia. Environ. Model. Softw.; 2016; 77, pp. 156-167. [DOI: https://dx.doi.org/10.1016/j.envsoft.2015.11.024]

187. Khanal, S.; Fulton, J.; Klopfenstein, A.; Douridas, N.; Shearer, S. Integration of High Resolution Remotely Sensed Data and Machine Learning Techniques for Spatial Prediction of Soil Properties and Corn Yield. Comput. Electron. Agric.; 2018; 153, pp. 213-225. [DOI: https://dx.doi.org/10.1016/j.compag.2018.07.016]

188. Albert, G.; Gerzsenyi, D. Slope Type Classification with Random Forest Method In The Gerecse Hills, Hungary. Proceedings of the 8th International Conference on Cartography and GIS; Nessebar, Bulgaria, 15–20 June 2020.

189. Tavares Wahren, F.; Tarasiuk, M.; Mykhnovych, A.; Kit, M.; Feger, K.-H.; Schwärzel, K. Estimation of Spatially Distributed Soil Information: Dealing with Data Shortages in the Western Bug Basin, Ukraine. Environ. Earth Sci.; 2012; 65, pp. 1501-1510. [DOI: https://dx.doi.org/10.1007/s12665-011-1197-3]

190. Samarinas, N.; Tsakiridis, N.L.; Kokkas, S.; Kalopesa, E.; Zalidis, G.C. Soil Data Cube and Artificial Intelligence Techniques for Generating National-Scale Topsoil Thematic Maps: A Case Study in Lithuanian Croplands. Remote Sens.; 2023; 15, 5304. [DOI: https://dx.doi.org/10.3390/rs15225304]

191. Li, Y.; Wang, C.; Wang, C.; Deng, X.; Zhao, Z.; Chen, S.; Lan, Y. Detection of the Foreign Object Positions in Agricultural Soils Using Mask-RCNN. Int. J. Agric. Biol. Eng.; 2023; 16, pp. 220-231. [DOI: https://dx.doi.org/10.25165/j.ijabe.20231601.7173]

192. Wu, T.; Luo, J.; Dong, W.; Sun, Y.; Xia, L.; Zhang, X. Geo-Object-Based Soil Organic Matter Mapping Using Machine Learning Algorithms with Multi-Source Geo-Spatial Data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.; 2019; 12, pp. 1091-1106. [DOI: https://dx.doi.org/10.1109/JSTARS.2019.2902375]

193. Wang, J.; Peng, J.; Li, H.; Yin, C.; Liu, W.; Wang, T.; Zhang, H. Soil Salinity Mapping Using Machine Learning Algorithms with the Sentinel-2 MSI in Arid Areas, China. Remote Sens.; 2021; 13, 305. [DOI: https://dx.doi.org/10.3390/rs13020305]

194. Yu, J.; Zheng, W.; Xu, L.; Meng, F.; Li, J.; Zhangzhong, L. TPE-CatBoost: An Adaptive Model for Soil Moisture Spatial Estimation in the Main Maize-Producing Areas of China with Multiple Environment Covariates. J. Hydrol.; 2022; 613, 128465. [DOI: https://dx.doi.org/10.1016/j.jhydrol.2022.128465]

195. Naghibi, S.A.; Khodaei, B.; Hashemi, H. An Integrated InSAR-Machine Learning Approach for Ground Deformation Rate Modeling in Arid Areas. J. Hydrol.; 2022; 608, 127627. [DOI: https://dx.doi.org/10.1016/j.jhydrol.2022.127627]

196. Arab, S.T.; Ahamed, T. Land Suitability Analysis for Potential Vineyards Extension in Afghanistan at Regional Scale Using Remote Sensing Datasets. Remote Sens.; 2022; 14, 4450. [DOI: https://dx.doi.org/10.3390/rs14184450]

197. Ramos, C.C.O.; Clerice, G.A.M.; Castro, B.A.; Silva Filho, N.M.; Ulson, J.A.C. Artificial Intelligence Techniques and Near-Infrared Spectroscopy for Nitrogen Content Identification in Sugar Cane Crops. Proceedings of the 2016 IEEE International Conference on Automatica (ICA-ACCA); Curico, Chile, 19–21 October 2016; pp. 1-5.

198. Silveira, C.T.; Oka-Fiori, C.; Santos, L.J.C.; Sirtoli, A.E.; Silva, C.R.; Botelho, M.F. Soil Prediction Using Artificial Neural Networks and Topographic Attributes. Geoderma; 2013; 195–196, pp. 165-172. [DOI: https://dx.doi.org/10.1016/j.geoderma.2012.11.016]

199. Fonseca-Luengo, D.; Lillo-Saavedra, M.; Lagos, L.O.; García-Pedrero, A.; Gonzalo-Martín, C. Use of Machine Learning to Improve the Robustness of Spatial Estimation of Evapotranspiration. Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, Proceedings of the 22nd Iberoamerican Congress, CIARP 2017, Valparaíso, Chile, 7–10 November 2017; Springer: Berlin/Heidelberg, Germany, 2018; pp. 237-245.

200. Cruz-Cárdenas, G.; Ortiz-Solorio, C.A.; Ojeda-Trejo, E.; Martínez-Montoya, J.F.; Sotelo-Ruiz, E.D.; Licona-Vargas, A.L. Computer-Assisted Cartography Using Topographic Properties: Precision and Accuracy of Local Soil Maps in Central Mexico. Rev. Bras. Cienc. Solo; 2011; 35, pp. 683-691. [DOI: https://dx.doi.org/10.1590/S0100-06832011000300003]

201. Cruz-Cárdenas, G.; Ortiz-Solorio, C.A.; Ojeda-Trejo, E.; Martínez-Montoya, J.F.; Sotelo-Ruiz, E.D.; Licona-Vargas, A.L. Evaluation of Four Digital Classifiers for Automated Cartography of Local Soil Classes Based on Reflectance and Elevation in Mexico. Int. J. Remote Sens.; 2010; 31, pp. 665-679. [DOI: https://dx.doi.org/10.1080/01431160902894491]

202. van Zijl, G. Digital Soil Mapping Approaches to Address Real World Problems in Southern Africa. Geoderma; 2019; 337, pp. 1301-1308. [DOI: https://dx.doi.org/10.1016/j.geoderma.2018.07.052]

203. Spencer, M.J.; Clark, R.; Mccullagh, J.; Whitfort, T. Classification of Dryland Salinity Risk Using Artificial Neural Networks. Proceedings of the 16th International Congress on Modelling and Simulation (MODSIM05); Melbourne, VIC, Canada, 12–15 December 2005.

204. Atzberger, C.; Rembold, F. Estimation of Inter-Annual Winter Crop Area Variation and Spatial Distribution with Low Resolution NDVI Data by Using Neural Networks Trained on High Resolution Images. Remote Sensing for Agriculture, Ecosystems, and Hydrology XI; SPIE Remote Sensing: Berlin, Germany, 2009; 747207.

205. Dutta, P.K.; Mitra, S. Application of Agricultural Drones and IoT to Understand Food Supply Chain during Post COVID-19. Agricultural Informatics; Wiley: Hoboken, NJ, USA, 2021; pp. 67-87.

206. Mahmoodian, V.; Jabbarzadeh, A.; Rezazadeh, H.; Barzinpour, F. A Novel Intelligent Particle Swarm Optimization Algorithm for Solving Cell Formation Problem. Neural Comput. Appl.; 2019; 31, pp. 801-815. [DOI: https://dx.doi.org/10.1007/s00521-017-3020-x]

207. Han, S.-Z.; Pan, W.-T.; Zhou, Y.-Y.; Liu, Z.-L. Construct the Prediction Model for China Agricultural Output Value Based on the Optimization Neural Network of Fruit Fly Optimization Algorithm. Future Gener. Comput. Syst.; 2018; 86, pp. 663-669. [DOI: https://dx.doi.org/10.1016/j.future.2018.04.058]

208. Khan, T.; Qiu, J.; Ali Qureshi, M.A.; Iqbal, M.S.; Mehmood, R.; Hussain, W. Agricultural Fruit Prediction Using Deep Neural Networks. Procedia Comput. Sci.; 2020; 174, pp. 72-78. [DOI: https://dx.doi.org/10.1016/j.procs.2020.06.058]

209. Jayasinghe, S.L.; Ranawana, C.J.K.; Liyanage, I.C.; Kaliyadasa, P.E. Growth and Yield Estimation of Banana through Mathematical Modelling: A Systematic Review. J. Agric. Sci.; 2022; 160, pp. 152-167. [DOI: https://dx.doi.org/10.1017/S0021859622000259]

210. Kasinathan, T.; Singaraju, D.; Uyyala, S.R. Insect Classification and Detection in Field Crops Using Modern Machine Learning Techniques. Inf. Process. Agric.; 2021; 8, pp. 446-457. [DOI: https://dx.doi.org/10.1016/j.inpa.2020.09.006]

211. Khan, F.S.; Khan, S.; Mohd, M.N.H.; Waseem, A.; Khan, M.N.A.; Ali, S.; Ahmed, R. Federated Learning-Based UAVs for the Diagnosis of Plant Diseases. Proceedings of the 2022 International Conference on Engineering and Emerging Technologies (ICEET); Kuala Lumpur, Malaysia, 27 October 2022; pp. 1-6.

212. Luo, C.; Liu, H.; Lu, L.; Liu, Z.; Kong, F.; Zhang, X. Monthly Composites from Sentinel-1 and Sentinel-2 Images for Regional Major Crop Mapping with Google Earth Engine. J. Integr. Agric.; 2021; 20, pp. 1944-1957. [DOI: https://dx.doi.org/10.1016/S2095-3119(20)63329-9]

213. Shen, Q.; Wang, Y.; Wang, X.; Liu, X.; Zhang, X.; Zhang, S. Comparing Interpolation Methods to Predict Soil Total Phosphorus in the Mollisol Area of Northeast China. Catena; 2019; 174, pp. 59-72. [DOI: https://dx.doi.org/10.1016/j.catena.2018.10.052]

214. Zhu, A.; Lu, G.; Liu, J.; Qin, C.; Zhou, C. Spatial Prediction Based on Third Law of Geography. Ann. GIS; 2018; 24, pp. 225-240. [DOI: https://dx.doi.org/10.1080/19475683.2018.1534890]

215. Gutiérrez, A. Irrigated Family Farming Panorama in the Latin-American Highlands. Cuad. Desarro. Rural; 2013; 10, pp. 93-114.

216. Peña-Azcona, I.; García-Barrios, R.; García-Barrios, L.; Ortega-Argueta, A.; Elizondo, C. The Unruly Complexity of Conservation Arrangements with Mexican Rural Communities: Who Really Funds the Game?. J. Rural. Stud.; 2021; 87, pp. 112-123. [DOI: https://dx.doi.org/10.1016/j.jrurstud.2021.08.027]

217. Muhammed, D.; Ahvar, E.; Ahvar, S.; Trocan, M.; Montpetit, M.-J.; Ehsani, R. Artificial Intelligence of Things (AIoT) for Smart Agriculture: A Review of Architectures, Technologies and Solutions. J. Netw. Comput. Appl.; 2024; 228, 103905. [DOI: https://dx.doi.org/10.1016/j.jnca.2024.103905]

218. Shi, Z.; Ferrari, G.; Ai, P.; Marinello, F.; Pezzuolo, A. Artificial Intelligence for Biomass Detection, Production and Energy Usage in Rural Areas: A Review of Technologies and Applications. Sustain. Energy Technol. Assess.; 2023; 60, 103548. [DOI: https://dx.doi.org/10.1016/j.seta.2023.103548]

219. Patel, A.; Kethavath, A.; Kushwaha, N.L.; Naorem, A.; Jagadale, M.; Sheetal, K.R.; Renjith, P.S. Review of Artificial Intelligence and Internet of Things Technologies in Land and Water Management Research during 1991–2021: A Bibliometric Analysis. Eng. Appl. Artif. Intell.; 2023; 123, 106335. [DOI: https://dx.doi.org/10.1016/j.engappai.2023.106335]

220. Goel, R.K.; Yadav, C.S.; Vishnoi, S.; Rastogi, R. Smart Agriculture—Urgent Need of the Day in Developing Countries. Sustain. Comput. Inform. Syst.; 2021; 30, 100512. [DOI: https://dx.doi.org/10.1016/j.suscom.2021.100512]

221. Othman, S.; Mavani, N.R.; Hussain, M.A.; Rahman, N.A.; Mohd Ali, J. Artificial Intelligence-Based Techniques for Adulteration and Defect Detections in Food and Agricultural Industry: A Review. J. Agric. Food Res.; 2023; 12, 100590. [DOI: https://dx.doi.org/10.1016/j.jafr.2023.100590]

222. Ayoub Shaikh, T.; Rasool, T.; Rasheed Lone, F. Towards Leveraging the Role of Machine Learning and Artificial Intelligence in Precision Agriculture and Smart Farming. Comput. Electron. Agric.; 2022; 198, 107119. [DOI: https://dx.doi.org/10.1016/j.compag.2022.107119]

223. Dhanush, G.; Khatri, N.; Kumar, S.; Shukla, P.K. A Comprehensive Review of Machine Vision Systems and Artificial Intelligence Algorithms for the Detection and Harvesting of Agricultural Produce. Sci. Afr.; 2023; 21, e01798. [DOI: https://dx.doi.org/10.1016/j.sciaf.2023.e01798]

224. Ayyildiz, E.; Yildiz, A.; Taskin, A.; Ozkan, C. An Interval Valued Pythagorean Fuzzy AHP Integrated Quality Function Deployment Methodology for Hazelnut Production in Turkey. Expert. Syst. Appl.; 2023; 231, 120708. [DOI: https://dx.doi.org/10.1016/j.eswa.2023.120708]

225. Alfred, R.; Obit, J.H.; Chin, C.P.-Y.; Haviluddin, H.; Lim, Y. Towards Paddy Rice Smart Farming: A Review on Big Data, Machine Learning, and Rice Production Tasks. IEEE Access; 2021; 9, pp. 50358-50380. [DOI: https://dx.doi.org/10.1109/ACCESS.2021.3069449]

226. Wang, Q.; Le Noë, J.; Li, Q.; Lan, T.; Gao, X.; Deng, O.; Li, Y. Incorporating Agricultural Practices in Digital Mapping Improves Prediction of Cropland Soil Organic Carbon Content: The Case of the Tuojiang River Basin. J. Environ. Manag.; 2023; 330, 117203. [DOI: https://dx.doi.org/10.1016/j.jenvman.2022.117203]

227. Talukdar, S.; Naikoo, M.W.; Mallick, J.; Praveen, B.; Shahfahad,; Sharma, P.; Islam, A.R.M.d.T.; Pal, S.; Rahman, A. Coupling Geographic Information System Integrated Fuzzy Logic-Analytical Hierarchy Process with Global and Machine Learning Based Sensitivity Analysis for Agricultural Suitability Mapping. Agric. Syst.; 2022; 196, 103343. [DOI: https://dx.doi.org/10.1016/j.agsy.2021.103343]