1. Introduction
1.1. Sustainable Building Environment (SBE)
A Sustainable Building Environment (SBE) refers to the integration of environmentally responsible and resource-efficient processes throughout a building’s lifecycle, from design and construction to operation, maintenance, and demolition [1,2]. The goal of an SBE is to reduce the environmental impact of buildings by promoting energy efficiency, minimizing waste, and utilizing sustainable materials. This approach considers various factors such as water conservation, air quality, and biodiversity. Buildings within an SBE are designed to be adaptable and resilient to changing climates, ensuring to provide healthy, comfortable environments for occupants while reducing carbon footprints and resource consumption [3,4]. By employing green building technologies, smart systems, and renewable energy sources, SBE aims to balance ecological considerations with social and economic benefits [5,6].
In addition to environmental aspects, SBEs emphasize the well-being of building occupants and broader communities by creating spaces that improve human health, productivity, and comfort. As in Figure 1, technologies such as Digital Twins (DT) and the Internet of Things (IoT) are increasingly integrated into SBEs to monitor and optimize performance in real-time, ensuring energy use is minimized without compromising on comfort or safety [7,8]. Furthermore, SBEs align with broader sustainability goals, such as zero-energy buildings, contributing to the overall transition toward more sustainable cities. As a result, SBEs improve the efficiency, effectiveness, and sustainability of managing buildings and infrastructure. It involves leveraging and urbanization [9,10].
1.2. Technology for Sustainable Building Environment (SBE)
Artificial Intelligence (AI), the Internet of Things (IoT), and Digital Twins (DT) are interconnected technologies that enhance decision-making, automation, and system optimization across various domains [8,11,12]. AI refers to the development of algorithms and systems that enable machines to perform tasks that typically require human intelligence, such as learning, reasoning, and problem-solving [13,14,15]. IoT involves a network of physical devices embedded with sensors, software, and connectivity, allowing them to collect and exchange data over the internet. DT, on the other hand, are virtual replicas of physical systems or objects that use real-time data from IoT devices to simulate, monitor, and analyze the performance of their physical counterparts based on AI analysis [11,16,17]. The relationship between these technologies is synergistic: IoT provides the data streams necessary to create and update DT, while AI analyzes this data to predict behaviors, optimize performance, and automate decisions, making these technologies a powerful combination for enhancing efficiency and innovation across industries [18,19,20].
AI, DT, and IoT can significantly enhance the sustainability, efficiency, and resilience of the building environment. IoT devices embedded within buildings collect real-time data on energy usage, temperature, humidity, occupancy, and equipment performance, creating a comprehensive digital ecosystem. This data feeds into DT, which serves as dynamic, virtual replicas of the physical building, enabling constant monitoring, simulation, and optimization of building systems [21,22,23]. AI processes this data, analyzing trends and predicting future behaviors to optimize energy consumption, automate lighting, heating, and cooling systems, and improve overall resource efficiency. In addition, AI-powered DT can simulate different scenarios, such as occupancy patterns or equipment failures, to identify potential inefficiencies and suggest proactive maintenance measures. Together, these technologies create smarter, more sustainable buildings that adapt in real-time to changing conditions, contributing to reduced energy consumption, lower carbon emissions, and improved occupant comfort and safety [22,24,25].
Figure 2 illustrates the integration of IoT-enabled physical buildings and Digital Twins, emphasizing a bi-directional communication loop between physical and digital assets. The physical building, equipped with IoT sensors, actuators, and systems, continuously collects real-time data (RTD) such as environmental conditions, equipment performance, and energy consumption and exchanges this data with the DT. AI analyzes the RTD and develops predictive analytics and simulations for DT using real-time computing (RTC). The DT serves as a virtual replica, performing real-time data analysis, fault detection, simulation forecasting, and interactive communication for predictive operations and optimization. The controllability aspect refers to IoT-enabled smart controls, which act on the insights provided by the DT to adjust building systems, improve operational efficiency, and integrate facilities management (IFM) throughout the building’s lifecycle. IFM refers to improving the efficiency, effectiveness, and sustainability of managing buildings and infrastructure. It involves leveraging technologies such as AI, IoT, and automation to optimize operations, reduce costs, and improve occupant experiences [26]. This continuous feedback loop allows for condition-based monitoring and lifecycle process improvement, ensuring the building remains adaptive, efficient, and optimized.
1.3. Research Objectives and Questions
A systematic literature review (SLR) is a structured research methodology that identifies, evaluates, and synthesizes all available evidence on a specific topic using predefined criteria and rigorous processes. It aims to provide a comprehensive, unbiased summary of existing knowledge to inform future research or practice [12,27]. The comparison in Table 1 reveals several gaps in existing literature related to DT, AI, and the IoT for the SBE. Past review papers have addressed specific aspects such as the role of DT in smart cities [16], the application of infrared thermography in buildings [1], and DT for healthy environments [17]. Blockchain integration with DT has also been reviewed, though without a focus on sustainability [6]. While some reviews have explored sustainable building practices through digital technologies [18] or the role of Industry 4.0 in enhancing manufacturing sustainability [19], the papers have not fully integrated AI, DT, and IoT into a comprehensive discussion of the sustainable building environment.
Moreover, the evolution of Building Information Modeling (BIM) into DT has been examined. However, future perspectives and limitations were minimally discussed [21]. In contrast, this paper addresses the identified gaps by systematically reviewing the integration of AI, DT, and IoT in SBE. It further explores the contributions of these technologies to sustainability while also identifying future research opportunities and limitations [20].
1.4. Research Objectives and Research Questions
The rapid advancement of AI-driven technologies, DT, and the IoT is reshaping the built environment, urban development, and industrial systems. As the demand for sustainable practices and smart systems grows, these technologies offer promising solutions for optimizing energy use, enhancing facility management, and fostering resilient infrastructure. This systematic literature review aims to investigate the scientometric trends and research directions across several key domains: DT in construction and facility management, integrating AI and IoT for energy optimization, and using emerging digital technologies in industry and urban sustainability. By exploring applications in smart cities, zero-energy buildings, heritage preservation, and flood resilience, this study identifies the most influential publications, emerging research clusters, and future opportunities for interdisciplinary collaboration. Through scientometric analysis, we aim to provide a comprehensive overview of how these technologies are advancing sustainability and efficiency in urban and industrial contexts. The research questions are as follows:
What are the research trends in DT, IoT, and AI for SBE?
What are the primary scientometric trends in AI and automation for manufacturing optimization in Industry 4.0?
What is the role of IoT and AI integration with Digital Twins in optimizing energy management and zero-energy building design?
How is AI-driven Digital Twin technology applied in heritage building maintenance and preservation?
What emerging technologies have shown the greatest promise for sustainable building practices and smart urban systems, according to scientometric reviews?
How has data management using AI evolved in urban and building systems for optimizing urban sustainability?
How have blockchain and cybersecurity measures been implemented in urban digital ecosystems, and what are the key research gaps?
What are the leading trends in data-driven approaches to building environment flood resilience, and how have they evolved?
How have Digital Twins contributed to sustainability and smart city initiatives based on published research over the past decade?
According to recent scientometric data, how has the integration of IoT, AI, and edge computing impacted manufacturing and production systems?
The gaps identified in the previous systematic literature review (SLR) papers primarily revolve around the fragmented scope of research and limited integration of key emerging technologies in sustainability and the built environment (SBE). For instance, while some reviews focus on specific applications like smart cities [21] or BIM evolving into Digital Twins (DT) [26], they lack a comprehensive analysis of the integration of AI, DT, and IoT technologies and their collective potential to optimize energy management, improve sustainability, and address future challenges. Additionally, many reviews, such as those on infrared thermography [1] and blockchain with DT [6], either fail to include critical aspects like future perspectives and interdisciplinary limitations or do not explore broader sustainability contexts. The detailed research questions (RQs) in this study address these gaps by systematically exploring the scientometric trends (RQ.1), AI and automation in Industry 4.0 (RQ.2), IoT and AI’s role in energy management and zero-energy buildings (RQ.3), and heritage building maintenance (RQ.4). The study also delves into emerging sustainable technologies (RQ.5), data management evolution (RQ.6), and blockchain and cybersecurity in digital ecosystems (RQ.7), ensuring a holistic analysis. By aligning these RQs with specific gaps in prior reviews, the study builds a detailed framework to explore overlooked areas, including flood resilience (RQ.8), DT’s contributions to smart cities (RQ.9), and the impact of IoT, AI, and edge computing on manufacturing systems (RQ.10). This structured approach ensures the study addresses key interdisciplinary challenges, offering new insights for sustainable urban and industrial systems.
2. Research Methodology
This research methodology presents a structured approach to conducting a scientometric analysis and classifying research pillars in a specific domain, as in Figure 3. The process begins with the identification of basic keywords relevant to the study (Building Environment, AI, Digital twins, and IoTs), which are then used to search academic databases such as Scopus and Web of Science (WoS). The search focuses on titles, abstracts, and keywords of publications. The initial set of papers is then subjected to inclusion and exclusion criteria to filter out irrelevant studies, resulting in a refined sample. After removing duplicates, the final sample of papers is obtained. Full-text scanning is performed on the final sample to gather detailed insights for further analysis.
The methodology is divided into two main branches: the scientometric analysis and the identification of research pillars. The scientometric analysis involves examining annual research trends, country-specific contributions, leading researchers, the involvement of various disciplines, and keyword frequency. This analysis provides a quantitative view of the research landscape. Simultaneously, the research pillars are developed through brainstorming and focus on applications-based classification, sustainability-based classification, and the identification of limitations and directions for future research. Together, these two branches guide a comprehensive understanding of the research domain, contributing to the development of insights into current trends, knowledge gaps, and future research opportunities. This study combines quantitative scientometric analysis by evaluating metrics like publication growth, citation patterns, and keyword trends with qualitative analysis of influential studies to interpret emerging themes, research gaps, and interdisciplinary connections. By integrating both approaches, it provides a holistic view of the field, linking statistical trends to contextual insights. This enables a deeper understanding of the impact and potential of technologies like AI, Digital Twins, and IoT in sustainable environments.
PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) is a guideline designed to improve the transparency and quality of reporting in systematic reviews and meta-analyses. It provides a structured checklist and flow diagram to ensure comprehensive and standardized documentation of the review process [27,34]. Figure 4 outlines a detailed process for identifying and refining a sample of research papers for a systematic review. Initially, 237 papers were identified based on keyword searches. These papers were then screened against predefined inclusion and exclusion criteria. The inclusion criteria limited the selection to papers published between 2018 and 2024 in English, which resulted in the exclusion of 29 papers. The remaining 208 papers underwent further screening based on exclusion criteria, which eliminated non-peer-reviewed publications, such as conference proceedings, book chapters, and non-research articles, leaving only peer-reviewed research articles and review papers. This step excluded an additional 83 papers, leading to a final sample of 125 papers. The method ensures a focused, high-quality dataset by prioritizing relevant, recent, and peer-reviewed research for the analysis.
3. Scientometric Analysis
Scientometric analysis is a quantitative approach used to evaluate the development and impact of scientific research within a specific field. It involves the systematic examination of research trends, publication outputs, and patterns of citation to identify key contributors, influential publications, and emerging themes. By analyzing factors such as the annual growth of publications, country-wise contributions, research collaborations, and the prevalence of specific keywords, scientometric analysis provides a comprehensive understanding of how a research area has evolved. In the context of emerging technologies such as AI, Digital Twins, and IoT in sustainable environments, this method helps map the trajectory of innovations, highlight influential works, and uncover gaps for future exploration. Ultimately, scientometric analysis offers valuable insights into the scientific landscape, enabling researchers and policymakers to track progress and set strategic directions for further research.
Figure 5 presents a comprehensive analysis of research activity and impact in the field of AI-driven Digital Twins and IoT for Sustainable Building Environments from 2018 to 2024. Two key trends are evident: a significant increase in the number of research papers published and a rapid growth in cumulative citations. The blue bars represent the annual count of published papers, while the yellow line illustrates the cumulative number of citations received by these papers. A clear upward trend is observed in both the number of papers and cumulative citations, indicating growing interest and research activity in this field. The trend line, visualized by the red dotted line, indicates a strong positive correlation between the number of papers and the cumulative citations, suggesting a significant impact on the published research. The high R2 value of 0.999 confirms the strength of this relationship.
From 2018 to 2024, the number of published papers has consistently increased, with a particularly sharp rise in 2023 and 2024. This trend suggests a surge in research interest and activity in AI-driven Digital Twins and IoT for SBE. Similarly, the cumulative citations have experienced a rapid increase, indicating that the published research is being widely cited and recognized by the scientific community. Therefore, the chart reveals a positive and accelerating trend in research activity and impact within the field of AI-driven Digital Twins and IoT for Sustainable Building Environments. The increasing number of published papers and cumulative citations highlight the growing importance and relevance of this research area.
Figure 6 is a pie chart that offers a comprehensive analysis of the research output in the field of AI-driven Digital Twins and IoT for SBE. Based on PRISMA, the final sample of filtered paper was 125 papers consisting of 97 articles and 28 review papers. The pie chart illustrates the distribution of citations across two types of academic publications: articles and reviews. Articles received 6634 citations (97 articles), while reviews received 4071 citations (28 review papers). The dominant category is articles, accounting for 97 papers and a total of 6634 citations. This indicates that the majority of research in this field is focused on original research studies, contributing significantly to the knowledge base. In contrast, reviews constitute a smaller proportion of the research output, with 28 papers and a total of 4071 citations. While reviews play a crucial role in synthesizing existing knowledge and providing critical perspectives, they represent a lesser volume of research compared to articles.
Table 2 presents the top-cited articles related to AI-driven digital twins (DT) and IoT for the sustainable building environment, reflecting their influence and contribution to the field. The highest-cited paper, Reference [16], published in Remote Sensing in 2022, focuses on the role of DT in smart cities, accumulating 455 citations. This is followed by Reference [1], a review on the applications of infrared thermography in buildings published in Renewable & Sustainable Energy Reviews, with 229 citations. Both articles emphasize the importance of digital technologies in advancing sustainability but focus on different applications within the built environment. Another notable paper is Reference [22], which proposes a framework for the circular economy in digital buildings, highlighting its relevance to sustainability with 208 citations, published in Sustainability.
Papers such as Reference [17], which reviews DT for ensuring healthy environments, and Reference [6], which explores blockchain integrated with DT, rank high in citations with 176 and 172, respectively. These reviews contribute to understanding DT’s role in improving environmental quality and secure management within the sustainable building context. Other influential works include Reference [18], which reviews sustainable buildings through digital technologies, and Reference [23], which discusses how Industry 4.0 technologies enable sustainability in the built environment. Therefore, most of these highly cited papers are review articles, signaling the ongoing need for comprehensive assessments of how AI, DT, and IoT converge to address sustainability challenges in buildings. The high citation counts reflect the growing academic and practical interest in these emerging technologies, highlighting their potential to revolutionize the construction and facility management industries.
The map and accompanying bar chart present the number of research papers published in various countries, as in Figure 7. The map visually highlights the concentration of research in specific regions. Countries with a higher number of published papers are represented by darker shades of blue, indicating a greater research activity. The bar chart provides a more detailed quantitative analysis, listing countries and their corresponding number of research papers.
China stands out as the leading country in this field, with a significantly higher number of published papers compared to other nations. This dominance suggests that China has made substantial investments and research efforts in AI-driven DT and IoT for SBE. The United States, the United Kingdom, and Australia follow China, demonstrating a strong research presence in this area. These countries have well-established research institutions and a conducive environment for innovation in the field of sustainable building technology. Other countries, such as Sweden, Switzerland, South Korea, Canada, and France, contribute to the research landscape, albeit to a lesser extent. These countries have shown growing interest and investment in AI-driven Digital Twins and IoT for Sustainable Building Environments, indicating a growing global recognition of the importance of this research area.
The researcher with the highest number of published documents is Jack C.P. Cheng, with 10 documents to his name. Following closely behind is Vincent J.L., as in Figure 8. Gan, Michal Grubel, Jascha Grubel, and Massimo Lauria, each with 10 documents published. A significant number of researchers have published between 2 and 5 documents, demonstrating a diverse range of research activity within the field. The researcher with the highest total link strength is Vincent J.L. Gan, with a score of 10. This indicates that his work has been widely cited and recognized by the scientific community. Jack C.P. Cheng and Michal Grubel also have high total link strengths of 10 each, suggesting that their research has had a significant impact on the field. Other researchers with notable total link strengths include Jascha Grubel (9), Massimo Lauria (8), and Xi Hu (7). The chart reveals a diverse landscape of researchers contributing to the field, with varying levels of productivity and impact. Some researchers have published a significant number of documents, indicating high research activity. However, the total link strength plays a crucial role in assessing a researcher’s influence. Researchers with a high total link strength have published influential works that have been widely cited and recognized by the scientific community.
The network diagram of key researchers offers a comprehensive analysis of the research landscape in AI-driven Digital Twins and IoT for SBE, as in Figure 9. The network illustrates the interconnectedness of key researchers, with Grubel Jascha serving as a central figure, facilitating collaborations and connecting different research groups. Other researchers, such as Aguilar, Leonel, and Sumner, Robert W., play significant roles as hubs, connecting multiple researchers and contributing to the field’s collaborative culture. While researchers such as Schinazi, Victor R., Thrash, Tyler, and Gath-Morad, Michal have fewer collaborative connections, their specialized areas of expertise contribute to the diversity and breadth of research in this field. Therefore, the network analysis reveals a strong culture of collaboration, highlights the importance of central figures in facilitating research, and identifies potential areas for future collaborations and knowledge exchange within the automated SBE.
Engineering is the dominant field, accounting for 34% of the research, as in Figure 10. Other significant disciplines include Computer Science (14%), Telecommunications (9%), Construction & Building (12%), and Electrical Engineering (8%). The presence of disciplines such as Chemistry (7%), Environmental Science (5%), Physics (5%), and Energy & Fuels (4%) underscores the interdisciplinary nature of the field, highlighting the need for collaboration among researchers from various backgrounds to address the challenges and opportunities in sustainable building technology.
The keywords network diagram visualizes the interconnectedness of key concepts and technologies within the field of AI-driven Digital Twins and IoT for SBE, as in Figure 11. The nodes in the network represent various research keywords such as “digital twin”, “internet of things”, “artificial intelligence”, and “sustainability”, while the lines connecting them indicate relationships or associations between these concepts. Central terms such as “digital twin” and “internet of things” serve as hubs, connecting multiple other concepts and highlighting their importance in the field. The network reveals the interdisciplinary nature of this research area, with connections between terms from different domains, such as engineering, computer science, and environmental science.
Figure 12 presents the most influential keywords in the study of “AI-powered Digital Twins and Internet of Things for Smart Cities and Sustainable Building Environment”, highlighting their significance through occurrences (blue bars) and total link strength (orange bars). Digital Twin emerges as the most influential keyword, with the highest total link strength of 89 and 48 occurrences, indicating its central role in advancing smart cities and sustainable building environments. Following this, the Internet of Things (IoT) demonstrates strong relevance with a total link strength of 85 and 36 occurrences, underscoring its importance in integrating AI-driven solutions across various domains.
Other notable keywords include Building Information Modeling (BIM), which shows a total link strength of 42 and 16 occurrences, reflecting its contribution to digital transformation in construction and urban planning. Artificial Intelligence (AI), with a link strength of 25 and 14 occurrences, highlights the growing use of AI in optimizing smart city operations. Similarly, Sustainability (34 link strength, 14 occurrences) and Smart Cities (24 link strength, 8 occurrences) emphasize the integration of environmentally friendly practices and urban innovation. Keywords like Machine Learning (22 link strength, 6 occurrences), Industry 4.0 (20 link strength, 8 occurrences), and Blockchain (21 link strength, 5 occurrences) illustrate emerging technologies’ roles in driving advancements. The Built Environment (19 link strength, 6 occurrences) and Construction (19 link strength, 5 occurrences) also highlight their ongoing significance in shaping modern, connected cities. These numbers collectively illustrate the multidisciplinary focus of the research and the interconnectedness of these technologies in enabling sustainable, AI-driven urban development.
4. Systematic Review of the Research Pillars
Digital Twins (DTs) driven by AI are essential for improving energy use in commercial buildings and greatly lowering carbon emissions. By integrating complex algorithms and real-time data, these systems improve energy management strategies, resulting in increased sustainability and efficiency. The main methods by which AI-powered DTs achieve these optimizations are outlined in the sections that follow:
Real-time monitoring and control: IoT integration, where DTs provide accurate monitoring and control of energy systems by using Internet of Things (IoT) sensors to collect real-time data on occupancy, energy usage, and environmental factors [39]. Also, the Adaptive HVAC Systems: Human-centered energy management systems optimize energy use while preserving comfort by modifying HVAC operations according to occupancy and preferences [40].
Predictive Analytics and Optimization, including Machine Learning Algorithms: AI methods, including Random Forest Regression, predict energy requirements and maximize power production in microgrids for smart buildings while balancing ecological and economic considerations [41]. In multi-objective Optimization, DTs provide intricate optimization scenarios, optimizing the use of renewable energy while lowering emissions and operating expenses [41].
Considering the significant advantages of AI-powered DTs, there are still obstacles to overcome in their implementation, such as the requirement for user involvement and the blending of various technologies. To fully utilize digital twins in energy management, several issues must be addressed. Figure 13 summarises the main pillars of the integration between digital twins and AI.
4.1. Digital Twins in the Built Environment
4.1.1. Applications of Digital Twins in Construction and Facility Management
There are many advantages to utilizing Digital Twins (DTs) in construction activities, and they can greatly improve project results. Throughout the project lifecycle, Digital Twins (DTs) enhance decision-making, efficiency, and collaboration by integrating real-time data and simulation capabilities. By providing a shared virtual visualization of the project, DTs promote transparency and empower stakeholders to assess progress and make informed decisions [42]. To ensure that stakeholders are on the same track during the modular building and operation phases, they facilitate information management and interchange [43]. Building Digital Twins (BDTs) enhances productivity and efficiency in construction site management by automating data collection and knowledge extraction, which reduces redundancies. Additionally, lean construction techniques, which aim to minimize waste and optimize processes, rely on constant monitoring and feedback loops enabled by DTs [42,44]. Digital Twins (DTs) enhance predictive capabilities by enabling proactive risk management and improving project outcome predictions through the simulation of multiple scenarios [32]. They use innovative technologies like AI and IoT, which could improve data safety and reliability while tackling prevalent issues in the construction industry [32]. Even though DTs have many advantages, issues regarding data integration and quality continue to be major obstacles to their broad use in the construction sector.
4.1.2. Sustainability and Smart Cities with Digital Twins
In smart cities, digital twins (DTs) are essential for improving sustainability and resource allocation since they offer predictive analytics and real-time data integration. Digital Twins (DTs) empower decision-makers and urban planners to maximize resource utilization, enhance productivity, and promote sustainable practices across various industries. For instance, in predictive maintenance, DTs anticipate infrastructure needs, enabling proactive interventions that reduce waste and extend asset life [45]. Digital Twins (DTs) enable dynamic resource allocation by modeling multiple scenarios to ensure the efficient use of energy, water, and other resources [46]. Additionally, DTs support sustainable urban planning by facilitating real-time analysis of environmental data, enabling the identification of suitable locations for renewable energy implementation and reducing carbon footprints [46].
Moreover, in Smart Agriculture, by using movable plant cultivation devices that can adjust to local conditions, digital twins can maximize urban agriculture and improve sustainability and food security [47]. Digital Twins (DTs) support data-driven decision-making by integrating diverse datasets, such as traffic and emissions statistics, to guide policy and urban planning decisions, ultimately fostering more sustainable outcomes [48]. By using scenario modeling, urban managers can investigate “what-if” scenarios and evaluate the possible effects of certain policies or advancements on sustainability [49].
4.1.3. Integration of IoT and AI with Digital Twins
By facilitating real-time monitoring, comprehensive analytics, and proactive decision-making, the combination of IoT and AI with digital twins greatly enhances maintenance forecasting in industrial settings. Improved efficiency and dependability are made possible by this synergy, which eventually lowers maintenance expenses and downtime. Digital twins enable the virtual representation of physical assets, facilitating data collection and real-time monitoring. This allows for continuous equipment performance tracking and optimization. Large volumes of data are gathered by IoT devices, and these data can be examined using AI algorithms to find trends and anticipate malfunctions before they happen [50,51].
Advanced analytics, powered by artificial intelligence (AI) techniques such as machine learning and deep learning, enhance the predictive capabilities of digital twins by analyzing complex datasets to forecast equipment failures [52,53]. In manufacturing settings, deep learning models, such as Autoencoders, have been effectively applied to enhance predictive maintenance outcomes [50]. This integration further supports decision-making by providing data-driven insights and actionable predictions. Real-time decision-making in response to operational difficulties is made easier by the integration of generative AI with digital twins, which enables scenario simulation and identification of anomalies [54,55]. By using this capability, industries can optimize system performance and dependability by implementing timely maintenance interventions [53,56].
The integration of deep learning and machine learning algorithms with digital twins leverages their predictive and analytical power to revolutionize maintenance forecasting and optimization in industrial applications. For instance, Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks are highly effective for analyzing time-series data generated by IoT sensors, enabling accurate predictions of equipment failures and performance trends [18,47,54]. Autoencoders, particularly denoising autoencoders, are employed for anomaly detection by reconstructing input data and identifying deviations indicative of faults. Frameworks like TensorFlow, PyTorch, and Apache MXNet facilitate the deployment of these models within digital twin systems by providing tools for training and integrating predictive algorithms. Additionally, algorithms such as Support Vector Machines (SVMs) and Gradient Boosting Machines (GBMs) are utilized for classification and regression tasks in predictive maintenance scenarios. By embedding these algorithms into digital twin platforms, industries can achieve robust, scalable solutions for real-time analytics, improving operational resilience and reducing costs [14,19,21].
4.1.4. Zero-Energy Building and Energy Optimization by IoT
IoT-based energy optimization systems, which use data analytics and cutting-edge technologies, are essential for lowering energy consumption and carbon footprints in zero-energy buildings (ZEBs). By integrating numerous elements, these systems allow for real-time energy resource monitoring and management, which significantly boosts sustainability and efficiency. IoT devices gather real-time data on environmental conditions and energy use, enabling dynamic adjustments to optimize energy consumption and distribution [42]. This approach enhances energy management by responding to changing conditions in real-time [57]. Advanced Algorithms such as metaheuristic algorithms and deep reinforcement learning maximize the performance of HVAC systems and renewable energy sources, resulting in an energy consumption decrease of up to 25% [58,59]. These systems ensure flexibility by balancing energy supply and demand through demand-side resources such as air cooling and battery storage. This approach reduces energy consumption while maintaining user comfort [60]. To achieve zero-energy targets, buildings must integrate renewable energy sources such as solar and wind into their energy systems. IoT enables this integration by facilitating real-time energy monitoring and control through hybrid systems [57,58]. Predictive models optimize the use of renewable energy by efficiently scheduling energy demands and reducing reliance on fossil fuels [59].
4.1.5. AI-Driven Heritage Building Maintenance
By integrating cutting-edge technologies and data analytics, AI-driven digital twins can significantly optimize the preservation of heritage structures while maintaining their historical integrity. These digital representations make informed decision-making, predictive maintenance, and real-time monitoring possible, guaranteeing that interventions preserve the building’s cultural significance. Data Integration for Maintenance, Building Information Modeling (BIM), and Heritage BIM (HBIM) are used in digital twins to generate dynamic models that mimic building behavior, enabling efficient maintenance schedules [61]. IoT devices gather data on structural health and environmental conditions in real-time, allowing for rapid interventions and ongoing monitoring [62,63]. A socio-technical approach enables an in-depth understanding of heritage structures by integrating social dynamics with building data, forming a framework for adaptive management [64]. According to Karatzas et al. [64], adaptive management is supported by the iterative system dynamics approach, which guarantees sustainability and resilience throughout time.
4.2. Digital Technologies and AI in Industry and Manufacturing
4.2.1. AI and Automation for Manufacturing Optimization
Several key performance indicators (KPIs) that represent operational effectiveness, quality, and economic impact can be utilized to assess how effectively AI and automation are working in manufacturing optimization. These KPIs allow firms to evaluate their progress toward strategic goals and are crucial tools for management and decision-making. The main KPIs related to this scenario are described in the sections that follow. KPIs for Operational Efficiency, focusing on Units Produced, indicate productivity levels by measuring the overall output over a given period [56,65]. Rework time measures how long it takes to fix errors, indicating the efficiency of the production process [65]. The defect rate, defined as the number of flaws per unit produced, provides data on process dependability and quality control [65]. KPIs for Economic Effectiveness assess how implementing AI has reduced operating expenses, which can be difficult to measure but are essential for determining profitability [66]. Return on Investment (ROI) Calculates the monetary gain from AI initiatives and assists in mitigating automation expenses [66]. KPIs for Predictive Performance, according to Chabane et al. [67], forecasting accuracy is the precision of forecasts regarding production outcomes that can be improved by machine learning approaches.
4.2.2. Industry 4.0 and Cyber-Physical Systems
Cyber-Physical Systems (CPS) and Industry 4.0 greatly improve supply chain efficiency and product customization by integrating digital technology and real-time data analytics. Manufacturers can increase overall operational performance, optimize production processes, and react quickly to market demands due to these advancements. According to Ullah et al. [68], Industry 4.0 technologies enhance supply chain efficiency by improving coordination, streamlining information flow, and reducing lead times. Process Innovation, IoT, and CPS integration promote creative procedures that lower costs and improve supply chain responsiveness [69]. Improvements to Security and advanced security methods, such as machine learning for anomaly detection, defend supply chain integrity, and ensure smooth operations [70,71,72]. While Industry 4.0 and CPS have numerous benefits, there are still drawbacks, such as the requirement for large investments in personnel development and technology. To fully realize the potential of these developments in supply chain management and production, these issues must be addressed.
4.2.3. IoT, AI, and Edge Computing in Manufacturing
For the integration of IoT, AI, and Edge Computing in the manufacturing sector to be successful, several significant obstacles and constraints must be overcome. The potential advantages of these technologies may be limited by these difficulties, which include operational, technological, and human aspects such as privacy and data Security. Strong cybersecurity measures are necessary since sensitive manufacturing data can be subject to cyberattacks [73,74]. Manufacturers are subject to data protection requirements, which might make implementation more difficult. Challenges with interoperability as the wide variety of platforms and devices used in production may cause problems with it. For efficient operation, it is essential to guarantee smooth communication between different IoT devices and AI systems [73,75,76]. These problems can be made harder by a lack of industry standards, which makes it more challenging to integrate new technology with current systems.
Professional Training and a workforce competent in AI and IoT technologies are necessary for the transition to smart manufacturing. It can take a lot of resources to hire fresh talent or upskill current staff [73,77]. Successful implementation may also be hampered by employee resistance to change. The infrastructure required to support sophisticated IoT and AI systems may be lacking in many manufacturing facilities. This covers network capabilities as well as physical infrastructure [75,78]. Although cutting-edge computing is useful for local data processing, it necessitates compatible hardware and software, which aren’t always easily accessible [74].
The integration of AI and edge computing in industrial applications significantly enhances productivity by enabling real-time data analysis, predictive maintenance, and optimized decision-making directly at the manufacturing site. Specific AI algorithms, such as convolutional neural networks (CNNs) for visual quality inspection and reinforcement learning for adaptive process control, facilitate automated operations with high precision [54,64]. Edge computing frameworks, like Kubernetes for edge orchestration or TensorFlow Lite for deploying lightweight AI models, ensure low-latency processing and reduce reliance on centralized cloud systems. This localized approach minimizes downtime by enabling predictive maintenance through anomaly detection algorithms and enhances operational efficiency by dynamically adjusting production parameters. Additionally, edge-enabled AI can ensure data privacy by processing sensitive information locally, aligning with stringent data protection regulations. These capabilities collectively foster a smarter, more agile manufacturing environment [19,39].
4.3. Sustainability in Urban Development
4.3.1. Ecological Output
In urban development, emerging technologies such as artificial intelligence (AI) and the Internet of Things (IoT) are essential for improving sustainable building practices. These technologies make it easier to gather and analyze data in real-time, which helps cities use resources more efficiently and use less energy. IoT and AI integration not only promotes sustainable urbanization but also successfully tackles environmental issues. AI-powered systems can forecast energy needs and modify municipal activities to reduce waste [79]. Building energy use is optimized by intelligent control systems, which drastically lower greenhouse gas emissions [80]. Also, IoT for Monitoring in Real Time data on energy use is gathered by IoT sensors, enabling quick changes to improve efficiency [81]. According to Singh et al. [81], this technology promotes environmentally friendly urban development by supporting sustainable mobility options and environmental monitoring. Despite the advantages, issues, including algorithm bias, data privacy, and implementation costs, need to be resolved [80,82]. For these technologies to be successfully adopted, comprehensive planning and citizen engagement are crucial [81].
4.3.2. Data Management and AI in Urban and Building Systems
To improve efficiency, sustainability, and quality of life in smart cities, data management and artificial intelligence (AI) must be integrated into building and urban systems. Better decision-making and operational performance result from this synergy, which makes it possible to handle the massive amounts of data produced by building management systems and urban infrastructures. AI-Powered Data Administration optimizes data processing in Smart Cities as high data quality (95.12% score) and privacy preservation (85.23% rate) are guaranteed by the AI-based Data Management System (AI-DMS [83]. To improve nuanced data sharing while preserving security, it uses a Multi-Level Sensitive Model for data classification [83]. Automation and Management Systems for Building is greatly enhanced by AI big data analytics, which makes it possible to do operations like performance optimization and energy anomaly detection [84]. Case studies show how real-time data analysis can improve operational efficiency through effective applications in both residential and business settings [84]. AI and IoT integrate to optimize urban administration and improve citizen experiences by enabling real-time data collection and autonomous analysis [85]. Applications that successfully handle urban difficulties include intelligent transportation and predictive maintenance [85].
4.3.3. Blockchain and Cybersecurity in Urban Digital Ecosystems
By taking full advantage of its special features, like decentralization, data integrity, and safe transaction capabilities, blockchain technology significantly improves cybersecurity in urban digital ecosystems. These characteristics can successfully reduce the dangers of data breaches and illegal access, which are common in complex urban settings. The main features of how blockchain can improve cybersecurity are described in the sections that follow.
The first feature is Data Integrity and Decentralization by using an open database, the blockchain reduces single points of failure and makes it more difficult for hackers to compromise the system [86]. The second is immutable records since sensitive data integrity is guaranteed by the blockchain’s inability to change or remove data after it has been recorded there [86]. The third is improved identity by verification and authentication and secure identification management, especially in urban metaverse applications, blockchain can enhance user identification verification procedures, lowering the danger of identity theft and impersonation [87]. The fourth is smart contracts, where only authorized parties can access or alter data, which can automate and safeguard transactions [88]. The fifth feature is employing it in Intelligent Urban Areas, and Blockchain can improve the security of interconnected systems and data transfers by protecting IoT devices in smart cities [86]. The sixth is data privacy, in urban digital ecosystems, methods such as Decentralized Privacy-Preserving Machine Learning can safeguard user data while preserving functionality [87].
4.3.4. EEG for Sustainable Building Environment
Electroencephalogram (EEG) technology integration in sustainable building environments provides significant data about how occupants’ cognitive performance and well-being are impacted by these spaces. Researchers can better understand the connection between the built environment and human experience by using EEG to detect brain activity objectively in reaction to different building designs. When compared to conventional buildings, EEG research has demonstrated that residents of sustainable buildings have better attentional focus and greater visual system involvement [89]. A decrease in cognitive load is shown by the regulation of brain activity, especially increased theta/delta activities, which foster awareness and improve mental health [89]. Another advantage is that Real-time feedback on how various spatial settings affect human perception and work efficiency is possible when EEG and virtual reality are combined [90].
Studies show that EEG β rhythms and task performance are significantly correlated, indicating that neurophysiological responses might be used to optimize building design [90]. Broad Implications for Sustainability: in line with the larger objectives of sustainable development, sustainable building methods consider not only environmental efficiency but also the psychological and social effects on inhabitants [91,92]. By encouraging healthier living conditions, the incorporation of EEG data can guide design procedures that improve occupant satisfaction and help achieve the UN Sustainable Development Goals [92].
4.3.5. Data-Driven Approaches to Build Environment Flood Resilience
The importance of data-driven methods in improving flood resilience in urban design is becoming more widely acknowledged. By utilizing cutting-edge technologies and approaches, cities may more accurately forecast, control, and lessen the impact of flooding. The best practices found in current research are described in the sections that follow.
The first usage is Big Data Analytics for traffic Flow Analysis; this is by analyzing human travel patterns using mobile phone signals, exposure hazards in flood-prone areas can be predicted with a 98.975% forecasting accuracy [93]. The second is Real-time monitoring during flood occurrences, timely notifications, and better decision-making, which is made possible by combining deep learning models with large data analytics [93]. The third technique is Model Predictive Control (MPC) system optimization, by improving system design, MPC improves urban stormwater management while lowering maximum flood depths and raising resilience indices [94]. The fourth is cost effectiveness, according to Chen et al. [94], the implementation of MPC delivers significant cost reductions in urban drainage systems in addition to improving flood prevention. The fifth is Geo-Computation Approaches via GIS and remote sensing. These technologies improve situational awareness during catastrophes by enabling efficient evacuation planning and real-time flood tracking [95]. The sixth is the integration of machine learning, adaptive response plans, and early warning systems, which can be developed by combining machine learning with geospatial data analytics [95]. The seventh is multidisciplinary frameworks, collaboration between different governing agencies is necessary for effective urban flood control, combining water resource management and land-use planning to build resilient urban settings [96,97]. The eighth is geographical factor analysis; this is by comprehending how urban subsystems interact, important drivers of flood resilience, like technology advancement and governmental authority, can be found [97].
4.4. Contribution to Sustainability
The following Figure 14 summarizes the points of application of DT supported by AI in the building environment. Each of these points is highlighted by the blue dot (real-time monitoring category) or green dot (forecasting category) some of them are both. With the aid of complex systems such as these, the economic trade-off (either monetary or ecological value) is easily monitored and could be highlighted. This would help the big cities to reduce, reuse, and recycle easily. It could also have the support of Industry 5.0 and further due to the automaticity of the demand-supply in not only the construction industry but all types as well. This will eventually support most of the developed and developing countries in their sustainable goals proposed by the UN. Specifically, this would aid in achieving goal no. 3: Good Health and Well-being, no. 7: Affordable and Clean Energy, no. 8: Decent Work and Economic Growth, no. 9: Industry, Innovation, and Infrastructure, no. 10: Reduced Inequalities, no. 11: Sustainable Cities and Communities, no. 12: Responsible Consumption and Production, no. 13: Climate Action, no. 15: Life on Land, and no. 17: Partnerships for the Goals.
5. Research Limitations and Future Research
The integration of AI-powered Digital Twins and IoT in smart cities and sustainable building environments faces several limitations that hinder broader implementation and impact [7,21,46]. A significant challenge is the lack of standardization across IoT devices, data formats, and protocols, which makes it difficult to create cohesive systems that communicate effectively. On the other hand, this lack of uniformity limits interoperability between devices and platforms, creating data silos that reduce the efficiency and effectiveness of Digital Twins. Additionally, data integration challenges are substantial; the vast amounts of data collected by IoT devices from various sources need to be harmonized, cleaned, and processed to generate actionable insights [14,22]. The heterogeneous nature of data collected from diverse devices in real-time complicates the process, often resulting in delays or inaccuracies in decision-making processes.
The key limitations and gaps in the implementation of AI-powered Digital Twins and IoT in smart cities and sustainable building environments are outlined in Figure 15. One primary limitation is the lack of standardized data protocols and integration frameworks, leading to fragmented systems and limited interoperability among various devices and platforms [50,54,98]. Additionally, challenges around data quality, privacy, and security are prevalent, as the vast amounts of information collected from IoT devices must be effectively managed to ensure reliability and user trust. Another gap is in the scalability of AI models to process real-time data continuously, which is critical for accurate predictions and effective decision-making in dynamic urban environments. Addressing these issues would require advancements in data standardization, security measures, and model scalability to fully realize the potential of Digital Twins and IoT in enhancing urban sustainability [14,30,33].
Efficient integration of heterogeneous data from different types of sensors is crucial for maintaining accurate and reliable digital twin models. Techniques such as data fusion, including Kalman filtering and Bayesian inference, can combine data from multiple sources to improve accuracy and consistency. Middleware platforms, such as Apache Kafka and MQTT, enable seamless integration and real-time data streaming from diverse IoT devices, ensuring low-latency communication [39,50,99]. To maintain data quality, preprocessing techniques such as normalization, outlier detection, and imputation address issues of noise and missing data. Furthermore, edge computing can preprocess and validate sensor data locally, reducing network load and ensuring real-time performance. Standardized communication protocols, such as OPC UA and IoT-specific APIs, enhance interoperability between disparate systems, ensuring that heterogeneous data sources contribute cohesively to the digital twin’s dynamic model, ultimately improving predictive capabilities and operational efficiency [9,28,48].
Future research in this field must address the standardization and interoperability challenges to enable seamless integration of AI-driven Digital Twins across urban and building systems. Developing universal standards for IoT devices and data protocols could pave the way for unified systems capable of supporting sustainable urban management at scale [50,64,91,100]. Furthermore, improving the scalability and flexibility of AI models to accommodate high-frequency data in real-time applications remains a significant challenge. As smart city initiatives grow in complexity, future research must also explore advanced data fusion techniques, such as federated learning and blockchain, for enhanced data security and privacy [8,33,35,101]. Addressing these limitations and challenges can enable AI-powered Digital Twins to drive more impactful outcomes in environmental sustainability, resource efficiency, and urban resilience, as in Figure 16.
6. Conclusions and Recommendations
This systematic literature review highlights the transformative potential of AI-powered Digital Twins and IoT in advancing sustainable building environments and smart city initiatives. By analyzing 125 studies, the review underscores the critical role of Digital Twins in construction and facility management, driving energy efficiency and sustainability through real-time data monitoring and predictive insights. The findings demonstrate that integrating IoT and AI can optimize building performance, support zero-energy building objectives, and enable more resilient urban planning. Additionally, the review identifies how AI and automation in manufacturing, particularly in Industry 4.0 settings, can streamline processes and enhance the adaptability of cyber-physical systems. Emerging technologies, such as blockchain for data security and EEG systems for real-time monitoring, further emphasize the potential of data-driven solutions to tackle pressing urban challenges, including flood resilience and cybersecurity in smart city infrastructures.
Several actions are recommended to maximize the benefits of AI-powered Digital Twins and IoT in sustainable building and urban contexts. First, developing standardized data protocols and interoperability frameworks is essential to address data integration challenges, enabling seamless communication between diverse IoT devices and platforms. Second, future research should focus on improving the scalability and flexibility of AI models to handle the dynamic and high-frequency data required for real-time applications in smart cities. Furthermore, integrating advanced data privacy and cybersecurity measures will be crucial for building trust in these technologies, particularly in sensitive applications like EEG-driven systems. Lastly, collaborations between academia, industry, and policymakers are vital for accelerating technological innovation and addressing regulatory challenges, ensuring that digital twin and IoT implementations align with sustainability goals and urban resilience priorities.
Conceptualization, A.A.A. and H.E.; data collection, H.E.; formal analysis; H.E.; funding acquisition, A.A.A.; investigation, A.A.A., M.M. and H.E.; methodology, H.E.; project administration, A.A.A. and H.E.; resources, A.A.A. and H.E.; software, H.E.; supervision, A.A.A. and H.E.; visualization, A.A.A., M.M. and H.E.; roles/writing—original draft A.A.A., M.M. and H.E.; writing—review and editing, A.A.A., M.M. and H.E. All authors have read and agreed to the published version of the manuscript.
Data will be made available on request.
There is no conflict among the authors.
| SBE | Sustainable building environment | CO2 | Carbon dioxide |
| DT | Digital twins | CO2 eq | Carbon dioxide equivalent |
| AI | Artificial intelligence | MAPE | Mean absolute percentage error |
| IoTs | Internet of Things | DNNs | Deep neural networks |
| ANN | Artificial Neural Networks | ML | Machine learning |
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.
![View Image - Figure 1. Sustainable building environment (SBE) technologies [7,8].](https://media.proquest.com/media/hms/THUM/2/QSU2b?_a=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%2BgIBWYIDA1dlYooDHENJRDoyMDI1MDcyNzEzMzIwMTk5NDo0NzA3MzA%3D&_s=bFrrFXGc3WltC3zCtZ3ifh6VhBQ%3D "View Image - Figure 1. Sustainable building environment (SBE) technologies [7,8].")
![View Image - Figure 2. Integration of Digital Twins, IoT, and AI for Smart Building Management [26].](https://media.proquest.com/media/hms/THUM/16/QSU2b?_a=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%2BgIBWYIDA1dlYooDHENJRDoyMDI1MDcyNzEzMzIwMTk5NDo0NzA3MzA%3D&_s=0tQbcGrG8y15eosq2nSes7klIsI%3D "View Image - Figure 2. Integration of Digital Twins, IoT, and AI for Smart Building Management [26].")
Enlarge this image.Figure 2. Integration of Digital Twins, IoT, and AI for Smart Building Management [26].
Comparison of past review papers.
| Reference | Main Objective | Year | Aspects | ||||
|---|---|---|---|---|---|---|---|
| Building Environment Scope | AI, DT, and IoT Integration | Sustainability | Future Perspectives and Limitations | SLR | |||
| [ | Review of DT in smart cities. | 2022 | × | × | √ | √ | √ |
| [ | Review of Infrared thermography applications in buildings. | 2022 | √ | × | √ | × | √ |
| [ | A review of DT ensuring healthy environments. | 2023 | √ | × | × | √ | × |
| [ | A review of Blockchain integrated with DT | 2023 | √ | √ | × | × | √ |
| [ | A review of sustainable building through digital technologies. | 2024 | × | √ | √ | × | √ |
| [ | A review for Industry 4.0 improving manufacturing sustainability. | 2021 | √ | × | √ | × | √ |
| [ | A review of DT applications in construction. | 2024 | × | × | √ | × | √ |
| [ | A review of BIM evolving into DT | 2021 | √ | × | √ | √ | × |
| This paper | A systematic review of AI, DT, and IoTs for SBE | 2024 | √ | √ | √ | √ | √ |
Top-cited articles about AI-driven Digital Twins and IoT for Sustainable Building Environment.
| Reference | Key Objective | Publication Year | Document Type | Citations | Journal |
|---|---|---|---|---|---|
| [ | Review of DT in smart cities. | 2022 | Review | 455 | Remote Sensing |
| [ | Review of Infrared thermography applications in buildings. | 2022 | Review | 229 | Renewable & Sustainable Energy Reviews |
| [ | A framework of circular economy in digital buildings. | 2021 | Article | 208 | Sustainability |
| [ | A review of DT ensuring healthy environments. | 2023 | Review | 176 | Frontiers Of Engineering Management |
| [ | A review of Blockchain integrated with DT | 2023 | Review | 172 | Sustainability |
| [ | A review of sustainable building through digital technologies. | 2024 | Review | 167 | Journal Of Cleaner Production |
| [ | Industry 4.0 technologies enable built environment sustainability. | 2024 | Article | 166 | Technology In Society |
| [ | A review for Industry 4.0 improving manufacturing sustainability. | 2021 | Review | 166 | Applied Sciences-Basel |
| [ | A review of DT applications in construction. | 2024 | Review | 164 | Buildings |
| [ | A review of BIM evolving into DT | 2021 | Review | 156 | Journal Of Information Technology In Construction |
| [ | IoT improving indoor air quality. | 2023 | Article | 149 | Science Of the Total Environment |
| [ | BIM-IoT integration for facility management. | 2021 | Review | 144 | Applied Sciences-Basel |
| [ | Digital twin enablers in buildings. | 2024 | Review | 143 | Energies |
References
1. Martin, M.; Chong, A.; Biljecki, F.; Miller, C. Infrared thermography in the built environment: A multi-scale review. Renew. Sustain. Energy Rev.; 2022; 165, 112540. [DOI: https://dx.doi.org/10.1016/j.rser.2022.112540]
2. Joensuu, T.; Edelman, H.; Saari, A. Circular economy practices in the built environment. J. Clean. Prod.; 2020; 276, 124215. [DOI: https://dx.doi.org/10.1016/j.jclepro.2020.124215]
3. Elmousalami, H.H.; Darwish, A.; Hassanien, A.E. The Truth About 5G and COVID-19: Basics, Analysis, and Opportunities. Digital Transformation and Emerging Technologies for Fighting COVID-19 Pandemic: Innovative Approaches; Studies in Systems, Decision and Control Hassanien, A.E.; Darwish, A. Springer International Publishing: Berlin/Heidelberg, Germany, 2021; Volume 322, pp. 249-259. [DOI: https://dx.doi.org/10.1007/978-3-030-63307-3_16]
4. Elmousalami, H.H. Sustainable Climate Change Policies Driven by Global CO2 Reduction During COVID-19. The Global Environmental Effects During and Beyond COVID-19; Studies in Systems, Decision and Control Hassanien, A.E.; Darwish, A.; Gyampoh, B.; Abdel-Monaim, A.T.; Anter, A.M. Springer International Publishing: Berlin/Heidelberg, Germany, 2021; Volume 369, pp. 121-136. [DOI: https://dx.doi.org/10.1007/978-3-030-72933-2_8]
5. Seyedrezaei, M.; Becerik-Gerber, B.; Awada, M.; Contreras, S.; Boeing, G. Equity in the built environment: A systematic review. Build. Environ.; 2023; 245, 110827. [DOI: https://dx.doi.org/10.1016/j.buildenv.2023.110827]
6. Mouratidis, K. Urban planning and quality of life: A review of pathways linking the built environment to subjective well-being. Cities; 2021; 115, 103229. [DOI: https://dx.doi.org/10.1016/j.cities.2021.103229]
7. Debrah, C.; Chan, A.P.; Darko, A. Artificial intelligence in green building. Autom. Constr.; 2022; 137, 104192. [DOI: https://dx.doi.org/10.1016/j.autcon.2022.104192]
8. Sadri, H.; Yitmen, I.; Tagliabue, L.C.; Westphal, F.; Tezel, A.; Taheri, A.; Sibenik, G. Integration of Blockchain and Digital Twins in the Smart Built Environment Adopting Disruptive Technologies—A Systematic Review. Sustainability; 2023; 15, 3713. [DOI: https://dx.doi.org/10.3390/su15043713]
9. Piras, G.; Agostinelli, S.; Muzi, F. Digital Twin Framework for Built Environment: A Review of Key Enablers. Energies; 2024; 17, 436. [DOI: https://dx.doi.org/10.3390/en17020436]
10. Fnais, A.; Rezgui, Y.; Petri, I.; Beach, T.; Yeung, J.; Ghoroghi, A.; Kubicki, S. The application of life cycle assessment in buildings: Challenges, and directions for future research. Int. J. Life Cycle Assess.; 2022; 27, pp. 627-654. [DOI: https://dx.doi.org/10.1007/s11367-022-02058-5]
11. Alnaser, A.A.; Ali, A.H.; Elmousalami, H.H.; Elyamany, A.; Mohamed, A.G. Assessment Framework for BIM-Digital Twin Readiness in the Construction Industry. Buildings; 2024; 14, 268. [DOI: https://dx.doi.org/10.3390/buildings14010268]
12. Elmousalami, H.H. Artificial Intelligence and Parametric Construction Cost Estimate Modeling: State-of-the-Art Review. J. Constr. Eng. Manag.; 2020; 146, 03119008. [DOI: https://dx.doi.org/10.1061/(ASCE)CO.1943-7862.0001678]
13. Zayed, S.M.; Attiya, G.M.; El-Sayed, A.; Hemdan, E.E.-D. A review study on digital twins with artificial intelligence and internet of things: Concepts, opportunities, challenges, tools and future scope. Multimed. Tools Appl.; 2023; 82, pp. 47081-47107. [DOI: https://dx.doi.org/10.1007/s11042-023-15611-7]
14. Kharchenko, V.; Illiashenko, O.; Morozova, O.; Sokolov, S. Combination of Digital Twin and Artificial Intelligence in Manufacturing Using Industrial IoT. Proceedings of the 2020 IEEE 11th International Conference on Dependable Systems, Services and Technologies; Kyiv, Ukraine, 14–18 May 2020; pp. 196-201.
15. Elmousalami, H.H.; Elaskary, M. Drilling stuck pipe classification and mitigation in the Gulf of Suez oil fields using artificial intelligence. J. Pet. Explor. Prod. Technol.; 2020; 10, pp. 2055-2068. [DOI: https://dx.doi.org/10.1007/s13202-020-00857-w]
16. Elmousalami, H.H. Comparison of Artificial Intelligence Techniques for Project Conceptual Cost Prediction: A Case Study and Comparative Analysis. IEEE Trans. Eng. Manag.; 2020; 68, pp. 183-196. [DOI: https://dx.doi.org/10.1109/TEM.2020.2972078]
17. ElMousalami, H.H.; Elyamany, A.H.; Ibrahim, A.H. Predicting Conceptual Cost for Field Canal Improvement Projects. J. Constr. Eng. Manag.; 2018; 144, 04018102. [DOI: https://dx.doi.org/10.1061/(ASCE)CO.1943-7862.0001561]
18. Xu, H.; Wu, J.; Pan, Q.; Guan, X.; Guizani, M. A Survey on Digital Twin for Industrial Internet of Things: Applications, Technologies and Tools. IEEE Commun. Surv. Tutor.; 2023; 25, pp. 2569-2598. [DOI: https://dx.doi.org/10.1109/COMST.2023.3297395]
19. Murthy, A.; Irshad, M.; Noman, S.M.; Tang, X.; Hu, B.; Chen, S.; Khader, G. Internet of Things, a vision of digital twins and case studies. IoT and Spacecraft Informatics; Elsevier: Amsterdam, The Netherlands, 2022; pp. 101-127.
20. Elmousalami, H.; Elmesalami, H.H.; Maxi, M.; Farid, A.A.M.; Elshaboury, N.A.T. A comprehensive evaluation of machine learning and deep learning algorithms for wind speed and power prediction. Decis. Anal. J.; 2024; 13, 100527. [DOI: https://dx.doi.org/10.1016/j.dajour.2024.100527]
21. Attaran, S.; Attaran, M.; Celik, B.G. Digital Twins and Industrial Internet of Things: Uncovering operational intelligence in industry 4.0. Decis. Anal. J.; 2024; 10, 100398. [DOI: https://dx.doi.org/10.1016/j.dajour.2024.100398]
22. Jacoby, M.; Usländer, T. Digital Twin and Internet of Things—Current Standards Landscape. Appl. Sci.; 2020; 10, 6519. [DOI: https://dx.doi.org/10.3390/app10186519]
23. Elmousalami, H.H.; Elshaboury, N.A.T.; Maxi, M.M.I.; Ibrahim, A.H.; Elyamany, A.H. Bayesian Optimized Ensemble Learning System for Predicting Conceptual Cost and Construction Duration of Irrigation Improvement Systems. KSCE J. Civ. Eng.; 2024; 100014. [DOI: https://dx.doi.org/10.1016/j.kscej.2024.100014]
24. Shishehgarkhaneh, M.B.; Keivani, A.; Moehler, R.C.; Jelodari, N.; Laleh, S.R. Internet of Things (IoT), Building Information Modeling (BIM), and Digital Twin (DT) in Construction Industry: A Review, Bibliometric, and Network Analysis. Buildings; 2022; 12, 1503. [DOI: https://dx.doi.org/10.3390/buildings12101503]
25. Elmousalami, H.; Elshaboury, N.; Elyamany, A.H. Green artificial intelligence for cost-duration variance prediction (CDVP) for irrigation canals rehabilitation projects. Expert Syst. Appl.; 2024; 249, 123789. [DOI: https://dx.doi.org/10.1016/j.eswa.2024.123789]
26. Elmousalami, H.H.; Mohamed, S.F. Multistage Optimization for Sustainable Zero Energy Residential Buildings on the Hot Arid Climat. 2022; Available online: http://jomardpublishing.com/UploadFiles/Files/journals/NDI/V6N3/Elmousalami_Mohamed.pdf (accessed on 7 September 2024).
27. Elmousalami, H.; Sakr, I. Artificial intelligence for drilling lost circulation: A systematic literature review. Geoenergy Sci. Eng.; 2024; 239, 212837. [DOI: https://dx.doi.org/10.1016/j.geoen.2024.212837]
28. Grübel, J.; Thrash, T.; Aguilar, L.; Gath-Morad, M.; Chatain, J.; Sumner, R.W.; Hölscher, C.; Schinazi, V.R. The Hitchhiker’s Guide to Fused Twins: A Review of Access to Digital Twins in Situ in Smart Cities. Remote Sens.; 2022; 14, 3095. [DOI: https://dx.doi.org/10.3390/rs14133095]
29. Cai, J.; Chen, J.; Hu, Y.; Li, S.; He, Q. Digital twin for healthy indoor environment: A vision for the post-pandemic era. Front. Eng. Manag.; 2023; 10, pp. 300-318. [DOI: https://dx.doi.org/10.1007/s42524-022-0244-y]
30. Asif, M.; Naeem, G.; Khalid, M. Digitalization for sustainable buildings: Technologies, applications, potential, and challenges. J. Clean. Prod.; 2024; 21, 141814. [DOI: https://dx.doi.org/10.1016/j.jclepro.2024.141814]
31. Jamwal, A.; Agrawal, R.; Sharma, M.; Giallanza, A. Industry 4.0 Technologies for Manufacturing Sustainability: A Systematic Review and Future Research Directions. Appl. Sci.; 2021; 11, 5725. [DOI: https://dx.doi.org/10.3390/app11125725]
32. Yang, Z.; Tang, C.; Zhang, T.; Zhang, Z.; Doan, D.T. Digital Twins in Construction: Architecture, Applications, Trends and Challenges. 2024; Available online: https://openrepository.aut.ac.nz/items/df976548-881f-4a83-9ca5-05a8ab42d969 (accessed on 13 October 2024).
33. Deng, M.; Menassa, C.C.; Kamat, V.R. From BIM to digital twins: A systematic review of the evolution of intelligent building representations in the AEC-FM industry. J. Inf. Technol. Constr.; 2021; 26, pp. 58-83. [DOI: https://dx.doi.org/10.36680/j.itcon.2021.005]
34. Sarkis-Onofre, R.; Catalá-López, F.; Aromataris, E.; Lockwood, C. How to properly use the PRISMA Statement. Syst. Rev.; 2021; 10, 117. [DOI: https://dx.doi.org/10.1186/s13643-021-01671-z]
35. Çetin, S.; De Wolf, C.; Bocken, N. Circular digital built environment: An emerging framework. Sustainability; 2021; 13, 6348. [DOI: https://dx.doi.org/10.3390/su13116348]
36. Pachouri, V.; Singh, R.; Gehlot, A.; Pandey, S.; Akram, S.V.; Abbas, M. Empowering sustainability in the built environment: A technological Lens on industry 4.0 Enablers. Technol. Soc.; 2024; 76, 102427. [DOI: https://dx.doi.org/10.1016/j.techsoc.2023.102427]
37. Dai, X.; Shang, W.; Liu, J.; Xue, M.; Wang, C. Achieving better indoor air quality with IoT systems for future buildings: Opportunities and challenges. Sci. Total Environ.; 2023; 895, 164858. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2023.164858] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/37343873]
38. Mannino, A.; Dejaco, M.C.; Re Cecconi, F. Building Information Modelling and Internet of Things Integration for Facility Management—Literature Review and Future Needs. Appl. Sci.; 2021; 11, 3062. [DOI: https://dx.doi.org/10.3390/app11073062]
39. Renganayagalu, S.K.; Bodal, T.; Bryntesen, T.-R.; Kvalvik, P. Optimising Energy Performance of buildings through Digital Twins and Machine Learning: Lessons learnt and future directions. Proceedings of the 2024 4th International Conference on Applied Artificial Intelligence (ICAPAI), IEEE; Halden, Norway, 16 April 2024; pp. 1-6.
40. Rafsanjani, H.N.; Nabizadeh, A.H.; Momeni, M. Digital Twin Energy Management System for Human-Centered Hvac and Mels Optimization in Commercial Buildings. 2024; Available online: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4837416 (accessed on 17 October 2024). [DOI: https://dx.doi.org/10.2139/ssrn.4837416]
41. Wang, Q.; Yin, Y.; Chen, Y.; Liu, Y. Carbon peak management strategies for achieving net-zero emissions in smart buildings: Advances and modeling in digital twin. Sustain. Energy Technol. Assess.; 2024; 64, 103661. [DOI: https://dx.doi.org/10.1016/j.seta.2024.103661]
42. Owais, O.A.; Poshdar, M.; Bidhendi, A.; Jaafar, K.; Sarhan, S. From Concept to Concrete: Digital Twins Enabling Different Levels of Lean Construction. Proceedings of the 32nd Annual Conference of the International Group for Lean Construction (IGLC 32); Auckland, New Zealand, 1–5 July 2024; pp. 767-779.
43. Yang, J.; Ng, S.T. Prospects for digital twin technology in the building modular construction and operation phases: A game theory-based analysis. J. Clean. Prod.; 2024; 470, 143344. [DOI: https://dx.doi.org/10.1016/j.jclepro.2024.143344]
44. Torres, J.; San-Mateos, R.; Lasarte, N.; Mediavilla, A.; Sagarna, M.; León, I. Building Digital Twins to Overcome Digitalization Barriers for Automating Construction Site Management. Buildings; 2024; 14, 2238. [DOI: https://dx.doi.org/10.3390/buildings14072238]
45. Ersan, M.; Irmak, E.; Colak, A.M. Applications, Insights and Implications of Digital Twins in Smart City Management. Proceedings of the 2024 12th International Conference on Smart Grid (icSmartGrid); Setubal, Portugal, 27–29 May 2024; pp. 378-383.
46. Wang, H.; Wang, Y. Smart Cities Net Zero Planning considering renewable energy landscape design in Digital Twin. Sustain. Energy Technol. Assess.; 2024; 63, 103629. [DOI: https://dx.doi.org/10.1016/j.seta.2024.103629]
47. Cardoso, J.L.F.P.; Rhodes, D.H. Digital Twin Use Case for Smart, Sustainable Cities. Proceedings of the 2023 Conference on Systems Engineering Research; Hoboken, NJ, USA, 16–17 March 2023; pp. 99-115. [DOI: https://dx.doi.org/10.1007/978-3-031-49179-5_7]
48. Sohail, A.; Shen, B.; Cheema, M.A.; Ali, M.E.; Ulhaq, A.; Babar, M.A.; Qureshi, A. Beyond Data, Towards Sustainability: A Sydney Case Study on Urban Digital Twins. arXiv; 2024; [DOI: https://dx.doi.org/10.48550/ARXIV.2406.04902] arXiv: 2406.04902
49. Pańkowska, M.; Żytniewski, M. Digital twins for smart city. Smart Spaces; Elsevier: Amsterdam, The Netherlands, 2024; pp. 269-286. [DOI: https://dx.doi.org/10.1016/B978-0-443-13462-3.00014-5]
50. Kerkeni, R.; Khlif, S.; Mhalla, A.; Bouzrara, K. Digital Twin Applied to Predictive Maintenance for Industry 4.0. J. Nondestruct. Eval. Diagn. Progn. Eng. Syst.; 2024; 7, 041008. [DOI: https://dx.doi.org/10.1115/1.4065875]
51. Al-Anzi, F.S.; Al-Anzi, A.F.; Sarath, S. Predictive maintenance in industrial IoT (IIoT). Proceedings of the International Conference on Medical Imaging, Electronic Imaging, Information Technologies, and Sensors (MIEITS 2024); Kuala Lumpur, Malaysia, 1–2 March 2024; pp. 9-105.
52. Ohoriemu, O.B.; Ogala, J.O. Integrating Artificial Intelligence and Mathematical Models for Predictive Maintenance in Industrial Systems. FUDMA J. Sci.; 2024; 8, pp. 501-505. [DOI: https://dx.doi.org/10.33003/fjs-2024-0803-2593]
53. Nadaf, S. AI for Predictive Maintenance in Industries. Int. J. Res. Appl. Sci. Eng. Technol.; 2024; 12, pp. 2013-2017. [DOI: https://dx.doi.org/10.22214/ijraset.2024.63442]
54. Muhammad, K.; David, T.; Nassisid, G.; Farus, T. Integrating Generative AI with Network Digital Twins for Enhanced Network Operations. arXiv; 2024; [DOI: https://dx.doi.org/10.48550/ARXIV.2406.17112] arXiv: 2406.17112
55. Mahdy, L.N.; Ezzat, K.A.; Elmousalami, H.H.; Ella, H.A.; Hassanien, A.E. Automatic x-ray COVID-19 lung image classification system based on multi-level thresholding and support vector machine. MedRxiv; 2020; 2020-03. [DOI: https://dx.doi.org/10.1101/2020.03.30.20047787]
56. Elmousalami, H.H.; Hassanien, A.E. Day Level Forecasting for Coronavirus Disease (COVID-19) Spread: Analysis, Modeling and Recommendations. arXiv; 2020; [DOI: https://dx.doi.org/10.48550/arXiv.2003.07778] arXiv: 2003.07778
57. Pateriya, N.; Thakre, N.; Kewat, P.K.; Vishwakarma, A. IoT in the Energy Sector: Revolutionizing Energy Management and Consumption. Int. J. Innov. Res. Comput. Commun. Eng.; 2023; 11, pp. 11344-11351. [DOI: https://dx.doi.org/10.15680/IJIRCCE.2023.1110050]
58. Lan, S.; Deprizon,; Razmjooy, N. Enhancing the performance of zero energy buildings with boosted coyote optimization and elman neural networks. Energy Rep.; 2024; 11, pp. 5214-5226. [DOI: https://dx.doi.org/10.1016/j.egyr.2024.05.001]
59. Gao, Y.; Li, S.; Xiao, Y.; Dong, W.; Fairbank, M.; Lu, B. An Iterative Optimization and Learning-Based IoT System for Energy Management of Connected Buildings. IEEE Internet Things J.; 2022; 9, pp. 21246-21259. [DOI: https://dx.doi.org/10.1109/JIOT.2022.3176306]
60. Zheng, Y.; Yu, K.; Chen, X.; Bu, L.; Xu, W.; Wang, S. Optimization of Energy Scheduling for Zero-carbon Buildings by Considering the Flexibility of Demand-side Air Conditioning System. Proceedings of the 2024 9th Asia Conference on Power and Electrical Engineering (ACPEE); Shanghai, China, 11–13 April 2024; pp. 901-907.
61. Garrigós, A.G.; López, J.L.-T. The use of Digital Twins for heritage conservation: The Church of San Juan del Hospital as a case study. Proceedings of the HEDIT 2024—International Congress for Heritage Digital Technologies and Tourism Management; Valencia, Spain, 20–21 June 2024.
62. Casillo, M.; Colace, F.; Gaeta, R.; Lorusso, A.; Santaniello, D.; Valentino, C. Revolutionizing cultural heritage preservation: An innovative IoT-based framework for protecting historical buildings. Evol. Intell.; 2024; 17, pp. 3815-3831. [DOI: https://dx.doi.org/10.1007/s12065-024-00959-y]
63. Maurmo, D.; Ruga, T.; Zumpano, E.; Vocaturo, E. Revolutionizing Structural Health Monitoring and Preserving Cultural Heritage via Digital Twins. Proceedings of the 2024 IEEE International Workshop on Metrology for Living Environment (MetroLivEnv); Chania, Greece, 12–14 June 2024; pp. 92-97.
64. Karatzas, S.; Lazari, V.; Fouseki, K.; Pracchi, V.N.; Balaskas, E. Digital twins-enabled heritage buildings management through social dynamics. J. Cult. Herit. Manag. Sustain. Dev.; 2024; [DOI: https://dx.doi.org/10.1108/JCHMSD-08-2023-0136]
65. Jeereddy, S.; Kennedy, K.; Duffy, E.; Walker, A.; Vorster, B. Machine Learning Use Cases for Smart Manufacturing KPIs. Proceedings of the 2019 IEEE International Conference on Big Data (Big Data); Los Angeles, CA, USA, 9–12 December 2019; pp. 4375-4380.
66. Vlasov, M.; Lapteva, A. Methods for Evaluating the Cost-Effectiveness of Using AI for Production Automation. Digital Transformation in Industry; Kumar, V.; Kyriakopoulos, G.L.; Akberdina, V.; Kuzmin, E. Springer Nature Switzerland: Cham, Switzerland, 2023; Volume 61, pp. 281-296. [DOI: https://dx.doi.org/10.1007/978-3-031-30351-7_22]
67. Chabane, A.N.; Sahnoun, M.; Bettayeb, B. Forecasting KPIs of Production Systems Using LSTM Networks. Proceedings of the 2021 1st International Conference on Cyber Management and Engineering (CyMaEn); Online, 26–28 May 2021; pp. 1-6.
68. Ullah, A.; Imran, S.; Roy, D. The Benefits of Using Industry 4.0 in the Manufacturing Sector. Industry 4.0 Technologies: Sustainable Manufacturing Supply Chains; Vimal, K.E.K.; Rajak, S.; Kumar, V.; Mor, R.S.; Assayed, A. Environmental Footprints and Eco-Design of Products and Processes Springer: Berlin/Heidelberg, Germany, 2024; pp. 83-103. [DOI: https://dx.doi.org/10.1007/978-981-99-4819-2_7]
69. Qureshi, K.M.; Mewada, B.G.; Kaur, S.; Alghamdi, S.Y.; Almakayeel, N.; Almuflih, A.S.; Qureshi, M.R.N.M. Sustainable Manufacturing Supply Chain Performance Enhancement through Technology Utilization and Process Innovation in Industry 4.0: A SEM-PLS Approach. Sustainability; 2023; 15, 15388. [DOI: https://dx.doi.org/10.3390/su152115388]
70. Abosuliman, S.S. Deep learning techniques for securing cyber-physical systems in supply chain 4.0. Comput. Electr. Eng.; 2023; 107, 108637. [DOI: https://dx.doi.org/10.1016/j.compeleceng.2023.108637]
71. Elmousalami, H.H.; Elyamany, A.H.; Ibrahim, A.H. Evaluation of Cost Drivers for Field Canals Improvement Projects. Water Resour. Manag.; 2018; 32, pp. 53-65. [DOI: https://dx.doi.org/10.1007/s11269-017-1747-x]
72. Elmousalami, H.H. Data on Field Canals Improvement Projects for Cost Prediction Using Artificial Intelligence. Data Brief; 2020; 31, 105688. [DOI: https://dx.doi.org/10.1016/j.dib.2020.105688] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/32490068]
73. Rath, K.C.; Khang, A.; Mishra, S.K.; Patnaik, P.K.; Mohanty, G.K.; Dash, T. Integration of Artificial Intelligence and Internet of Things Technology Solutions in Smart Manufacturing. Machine Vision and Industrial Robotics in Manufacturing; 1st ed. CRC Press: Boca Raton, FL, USA, 2024; pp. 155-177. [DOI: https://dx.doi.org/10.1201/9781003438137-9]
74. Miran, A.Z.; Ayub, H. The Investigation and Challenges of Advanced Applications Using Artificial IoT on Edge Computing. Qalaai Zanist Sci. J.; 2023; 8, pp. 1361-1375. [DOI: https://dx.doi.org/10.25212/lfu.qzj.8.2.55]
75. Awaisi, K.S.; Ye, Q.; Sampalli, S. A Survey of Industrial AIoT: Opportunities, Challenges, and Directions. IEEE Access; 2024; 12, pp. 96946-96996. [DOI: https://dx.doi.org/10.1109/ACCESS.2024.3426279]
76. Beseiso, M.; Elmousalami, H. Subword Attentive Model for Arabic Sentiment Analysis: A deep learning approach. ACM Trans. Asian Low-Resour. Lang. Inf. Process.; 2020; 19, pp. 1-17. [DOI: https://dx.doi.org/10.1145/3360016]
77. Matin, A.; Islam, M.R.; Wang, X.; Huo, H.; Xu, G. AIoT for sustainable manufacturing: Overview, challenges, and opportunities. Internet Things; 2023; 24, 100901. [DOI: https://dx.doi.org/10.1016/j.iot.2023.100901]
78. Gibbs, M.; Kanjo, E. Realising the Power of Edge Intelligence: Addressing the Challenges in AI and tinyML Applications for Edge Computing. Proceedings of the 2023 IEEE International Conference on Edge Computing and Communications (EDGE); Chicago, IL, USA, 2–8 July 2023; pp. 337-343.
79. Jakkani, A.K. Enhancing Urban Sustainability through AI-Driven Energy Efficiency Strategies in Cloud-Enabled Smart Cities. J. Energy Eng. Thermodyn.; 2024; 4, pp. 1-13. [DOI: https://dx.doi.org/10.55529/jeet.45.1.13]
80. Adewale, B.A.; Ene, V.O.; Ogunbayo, B.F.; Aigbavboa, C.O. Application of Artificial Intelligence (AI) in Sustainable Building Lifecycle; A Systematic Literature Review. Buildings; 2024; 14, 2137. [DOI: https://dx.doi.org/10.3390/buildings14072137]
81. Hemanth Kumar, S.; Prabha, K.; Mahalakshmi, S.; Dinesh, N.; Anantha Subramanya Iyer, K.N. Technology’s Role in Sustainable Urban Development in Smart Cities. Advances in Human Resources Management and Organizational Development; Singh, K.; Yadav, J.; Abraham, R. IGI Global: Hershey, PA, USA, 2024; pp. 169-208. [DOI: https://dx.doi.org/10.4018/979-8-3693-3238-2.ch008]
82. Al-Raeei, M. The smart future for sustainable development: Artificial intelligence solutions for sustainable urbanization. Sustain. Dev.; 2024; sd.3131. [DOI: https://dx.doi.org/10.1002/sd.3131]
83. Jyothi, D.; Sreelatha, T.; Thiyagu, D.; Sowndharya, R.; Arvinth, N. A Data Management System for Smart Cities Leveraging Artificial Intelligence Modeling Techniques to Enhance Privacy and Security. J. Internet Serv. Inf. Secur.; 2024; 14, pp. 37-51. [DOI: https://dx.doi.org/10.58346/JISIS.2024.I1.003]
84. Himeur, Y.; Elnour, M.; Fadli, F.; Meskin, N.; Petri, I.; Rezgui, Y.; Bensaali, F.; Amira, A. AI-big data analytics for building automation and management systems: A survey, actual challenges and future perspectives. Artif. Intell. Rev.; 2023; 56, pp. 4929-5021. [DOI: https://dx.doi.org/10.1007/s10462-022-10286-2] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/36268476]
85. Van Hoang, T. Impact of Integrated Artificial Intelligence and Internet of Things Technologies on Smart City Transformation. J. Tech. Educ. Sci.; 2024; 19, pp. 64-73. [DOI: https://dx.doi.org/10.54644/jte.2024.1532]
86. C, V.; Golabhavi, R.; Reddy, P.; Kumar, P. Enhancing Cyber Security through the utilization of Blockchain Technology. Int. J. Innov. Res. Inf. Secur.; 2023; 9, pp. 92-96. [DOI: https://dx.doi.org/10.26562/ijiris.2023.v0903.10]
87. Kuru, K.; Kuru, K. Blockchain-Based Decentralised Privacy-Preserving Machine Learning Authentication and Verification with Immersive Devices in the Urban Metaverse Ecosystem. Preprints; 2024; 2024020317. [DOI: https://dx.doi.org/10.20944/preprints202402.0317.v1]
88. Ahmed, A.A. The Role of Blockchain Technology in Enhancing Cybersecurity. Int. J. Sci. Res. Eng. Manag.; 2024; 2, pp. 144-152. [DOI: https://dx.doi.org/10.55041/IJSREM35012]
89. Hu, M.; Simon, M.; Fix, S.; Vivino, A.A.; Bernat, E. Exploring a sustainable building’s impact on occupant mental health and cognitive function in a virtual environment. Sci. Rep.; 2021; 11, 5644. [DOI: https://dx.doi.org/10.1038/s41598-021-85210-9]
90. Li, J.; Jin, Y.; Lu, S.; Wu, W.; Wang, P. Building environment information and human perceptual feedback collected through a combined virtual reality (VR) and electroencephalogram (EEG) method. Energy Build.; 2020; 224, 110259. [DOI: https://dx.doi.org/10.1016/j.enbuild.2020.110259]
91. Grierson, D. Towards Sustainable Building Design. Des. Princ. Pract. Int. J. Annu. Rev.; 2009; 3, pp. 143-152. [DOI: https://dx.doi.org/10.18848/1833-1874/CGP/v03i03/37682]
92. Scrucca, F.; Ingrao, C.; Barberio, G.; Matarazzo, A.; Lagioia, G. On the role of sustainable buildings in achieving the 2030 UN sustainable development goals. Environ. Impact Assess. Rev.; 2023; 100, 107069. [DOI: https://dx.doi.org/10.1016/j.eiar.2023.107069]
93. Malik, V.; Martin, R.J.; Mittal, R.; Ravali, R.S.; Almalki, K.J.; Ramakrishnan, J.; Swapna, S.L.; Mavaluru, D.; Goyal, S.B.; Kumar, M. Enhancing Urban Resilience to Flooding in Hydrogeological Risk Areas Through Big Data Analytics Using Deep Neuro-Fuzzy System. Preprint; 2024; [DOI: https://dx.doi.org/10.21203/rs.3.rs-4615497/v1]
94. Chen, T.; Chen, L.; Shao, Z.; Chai, H. Enhanced resilience in urban stormwater management through model predictive control and optimal layout schemes under extreme rainfall events. J. Environ. Manag.; 2024; 366, 121767. [DOI: https://dx.doi.org/10.1016/j.jenvman.2024.121767] [PubMed: https://www.ncbi.nlm.nih.gov/pubmed/38986369]
95. Jain, H. Leveraging geo-computational innovations for sustainable disaster management to enhance flood resilience. Discov. Geosci.; 2024; 2, 33. [DOI: https://dx.doi.org/10.1007/s44288-024-00042-0]
96. Huang, C.-C.; Wang, C.-L. Enhancing urban flood resilience: Interdisciplinary integration of climate adaptation, flood control, and land-use planning from 3PA to 4PA. J. Water Clim. Change; 2024; 15, pp. 1961-1968. [DOI: https://dx.doi.org/10.2166/wcc.2024.125]
97. Zhu, S.; Feng, H.; Arashpour, M.; Zhang, F. Enhancing urban flood resilience: A coupling coordinated evaluation and geographical factor analysis under SES-PSR framework. Int. J. Disaster Risk Reduct.; 2024; 101, 104243. [DOI: https://dx.doi.org/10.1016/j.ijdrr.2024.104243]
98. Mondejar, M.E.; Avtar, R.; Diaz, H.L.B.; Dubey, R.K.; Esteban, J.; Gómez-Morales, A.; Hallam, B.; Mbungu, N.T.; Okolo, C.C.; Prasad, K.A. et al. Digitalization to achieve sustainable development goals: Steps towards a Smart Green Planet. Sci. Total Environ.; 2021; 794, 148539. [DOI: https://dx.doi.org/10.1016/j.scitotenv.2021.148539]
99. Li, L.; Qu, T.; Liu, Y.; Zhong, R.Y.; Xu, G.; Sun, H.; Gao, Y.; Lei, B.; Mao, C.; Pan, Y. et al. Sustainability Assessment of Intelligent Manufacturing Supported by Digital Twin. IEEE Access; 2020; 8, pp. 174988-175008. [DOI: https://dx.doi.org/10.1109/ACCESS.2020.3026541]
100. Hammam, A.A.; Elmousalami, H.H.; Hassanien, A.E. Stacking Deep Learning for Early COVID-19 Vision Diagnosis. Big Data Analytics and Artificial Intelligence Against COVID-19: Innovation Vision and Approach; Studies in Big Data Hassanien, A.-E.; Dey, N.; Elghamrawy, S. Springer International Publishing: Berlin/Heidelberg, Germany, 2020; Volume 78, pp. 297-307. [DOI: https://dx.doi.org/10.1007/978-3-030-55258-9_18]
101. Elmousalami, H.H. Closure to “Artificial Intelligence and Parametric Construction Cost Estimate Modeling: State-of-the-Art Review” by Haytham, H. Elmousalami. J. Constr. Eng. Manag.; 2021; 147, 07021002. [DOI: https://dx.doi.org/10.1061/(ASCE)CO.1943-7862.0002049]
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Details
; Elmousalami, Haytham 3 1 Department of Architecture and Building Science, Collage of Architecture and Planning, King Saud University, Riyadh 11574, Saudi Arabia
2 Industrial Ecology, Energy and Process Engineering, Norwegian University of Science and Technology (NTNU), 7034 Trondheim, Norway;
3 Infrastructure Department, Faculty of Engineering and IT, University of Melbourne, Parkville, VIC 3010, Australia;