Author: Sajjad Naseri
Department of Civil, Chemical, Environmental, and Materials Engineering – DICAM, Alma Mater Studiorum - Università di Bologna, Italy
Source: "Advances in Civil Engineering and Environmental Science" Journal (ACEES)
Volume 2, Issue 1, February 2025, Pages 90-101
DOI: https://doi.org/10.22034/acees.2025.488106.1013
ABSTRACT
This study explores the transformative role of artificial intelligence (AI) in designing and managing sustainable urban environments. Through a comprehensive literature review, we examined topics such as AI, sustainable architecture, smart cities, urban planning, and energy efficiency, selecting articles that provide significant insights into AI's influence on the built environment. The research highlights how AI-driven innovations, including data-driven decisionmaking, energy optimization, and predictive maintenance, enhance urban infrastructures' efficacy, resilience, and sustainability. Case studies demonstrate AI's impact on energy-efficient building design, smart materials selection, and intelligent urban systems such as traffic management, water distribution, and waste management. AI-powered tools, such as generative design and predictive analytics, enable architects and urban planners to create adaptive, resource-efficient solutions that address global urbanization and climate challenges. However, challenges such as data interoperability, ethical concerns, and computational demands remain. Despite these limitations, AI is poised to set new benchmarks for sustainable urban development, promoting flexible, ecologically friendly ecosystems. AI holds immense potential to redefine urban design and management, fostering innovative, sustainable solutions to global urban challenges.
1. Introduction
1.1. Significance of AI in the built environment
Artificial intelligence increasingly transforms building design and urban planning, with widespread applications in modern practices. AI introduces innovative applications that help design and optimize sustainable, intelligently built environments. The present study delves into how Artificial Intelligence (AI) impacts the creation and study of intelligent built environments. The use of AI in design is demonstrated by the study undertaken by As et al. (2018), who explore the use of learning for creating conceptual designs. Their research demonstrates how AI can assist architects in developing design solutions that enhance form and function. Based on their studies, deep learning algorithms can scrutinize data to generate design ideas that fulfil requirements such as energy efficiency and visual attractiveness (As et al., 2018).
Chaillou (2020) explores the relationship between AI and architecture through the Archigan project. This effort illustrates how artificial intelligence may enhance design and robotic manufacturing processes. Caillou’s research emphasizes how AI can revolutionize practices by simplifying activities and encouraging innovative and practical design solutions. According to their study, tools based on AI can notably cut down on the time and energy needed to formulate and refine ideas, resulting in inventive and environmentally friendly results. Ganin et al. (2021) offer a unique perspective on how computer-aided design functions as a form of communication, stressing the role of artificial intelligence in enhancing exchange and teamwork in design. Their research points out that AI has the capability to support more efficient design workflows by converting complex design ideas into clear and usable forms. They state, "Tools powered by AI can close the divide among various participants in the design journey, facilitating smoother teamwork and more accurate choices". Liao et al. (2022) presented an innovative approach to structural design with Generative Adversarial Networks, GANs. They used shear wall constructions to implement this technique. Their work shows AI can advance structural design by generating innovative solutions that satisfy performance standards. The research shows that GANbased design methods can produce highly optimized structural designs that enhance building performance while reducing material use and construction costs. Tarabishy et al. (2021) Investigated the effects of AI on the built environment within the industry context. Their research demonstrates how AI can revolutionize urban planning, intelligent building management, and construction automation. They assert that AI technologies can significantly enhance the efficiency and sustainability of built environments through real-time monitoring, predictive maintenance, and informed decision-making based on data analysis.
Collecting data from Google Street View, Chen et al. (2024) explored the influence of urban characteristics on heart disease. They found that artificial intelligence (AI) could provide valuable insights into how urban planning impacts health, and they highlight the importance of considering health factors in city design. They suggest that AI can identify critical elements of cities that affect public health. They suggest the creation of better city planning and policy. Finally, Luusua et al. (2023) analyze the growing importance of artificial intelligence (AI) in intelligent cities, emphasizing how AI might improve quality of life, sustainability, and efficiency in urban areas. Their research explores the potential of AI to address urban challenges such as waste management, energy consumption, and traffic congestion. They highlight that AI could play a crucial role in creating more intelligent, more sustainable cities by optimizing urban systems and enabling more flexible and adaptive strategies for urban governance.
These studies demonstrate AI's significant impact on the built environment, highlighting its potential to enhance efficiency, sustainability, and urban quality of life. This analysis aims to provide readers with a comprehensive understanding of these advancements while identifying areas that require further exploration to drive future innovation.
1.2. Definition of key terms
Artificial Intelligence (AI) is the term used to describe the simulation of human intellect in machines and learning applications. AI in the built environment includes technologies that can assess data, make judgments, and improve over time, such as machine learning and neural networks. Sustainability in the built environment is about planning buildings and metropolitan areas. It is thinking about meeting present needs without negatively affecting future resources. The primary objectives are to reduce environmental effects and maximize resource use. Intelligent Built Spaces is the process of making computers think like people. Neural networks and machine learning are two examples of the technology involved. These are employed for data analysis to make decisions about enhancing the built environment. Table 1 defines key terms to clarify concepts central to AI, sustainability, and smart built environments.
Table 1 Definition of key terms
2. Methodology
2.1. Literature selection criteria
This study aimed to investigate the use of AI in sustainable built environments. AI in the built environment is the main topic of the study. Important earlier studies and more recent research were included to balance key ideas and current advancements. Additional literature containing data, case studies, or reviews on AI's effects on the built environment was included to provide an extensive understanding of the subject.
2.2. Databases and sources used for literature search
The IEEE Xplore, ScienceDirect, SpringerLink, and Web of Science were notable sources of peer-reviewed articles and conference proceedings in engineering, technology, and environmental sciences. Various publications, including reports from reputable organizations and grey literature, were also gathered using Google Scholar. A large number of publications are used to assess the most critical research.
2.3. Inclusion and exclusion criteria
Inclusion criteria for this review were established to focus on high-quality, peer-reviewed studies published within the last decade to reflect the latest advancements in AI and its applications in the built environment. Articles mainly discussed AI technology in smart cities and sustainable building design or similar disciplines were chosen. Research published in non-peer-reviewed journals or beyond the purview of AI applications in the built environment was disqualified.
2.4. Summary of the literature review process
To begin with, we looked for papers for the literature review. Artificial intelligence, sustainable architecture, smart cities, urban planning, and energy efficiency are some of the terms we utilized. We looked through many articles to determine what should be included and what shouldn't. After thoroughly examining abstracts and full texts, a final selection of articles focused on those that provided notable insights into the impact of AI on the built environment. The foundation for this investigation was created by combining the key ideas and findings from the carefully selected literature.
3. AI in Sustainable Building Design
3.1. Sustainable architecture
AI contributes to sustainable design by developing green solutions in various ways. To make buildings more environmentally and energy-efficiently friendly, it is possible to predict energy use patterns better and maximize the use of renewable energy sources. Artificial intelligence (AI) empowers architects to estimate the environmental impacts of multiple designs and, thereafter, simulate the outcomes of these models to realize more green and sustainable buildings by implementing AI into sustainability (Tarabishy et al., 2021).
Artificial intelligence is being used widely in sustainable design, one key use being the analysis of large datasets about building efficiency using machine learning algorithms. These algorithms can identify patterns that help design decisions, like which way a structure should face and which materials to employ that save energy. AI systems can predict a building's energy needs by analyzing variables such as occupancy and weather. It allows for more accurate energy management plans (Awuzie et al., 2024).
AI also facilitates the integration of intelligent systems within buildings and enhances their sustainability. Artificial intelligence (AI)- powered bright lighting, heating, and cooling systems adapt automatically to changing circumstances, saving energy and enhancing occupant comfort. AI solutions reduce waste and assist in making better use of available resources (Osuizugbo et al., 2021). Architects are using AI to develop tools to rapidly test various design concepts while consuming less energy and causing less environmental damage (Chew et al., 2024).
3.2. Energy-efficient building design
AI is crucial to the success of sustainable design, which heavily emphasizes energy efficiency. AI-powered energy modelling and simulation technologies assist architects in creating energy-efficient, livable, and practical structures. Machine learning algorithms can forecast a building's energy consumption and adjust to reduce it and save gas. Artificial neural networks are one standard AI technology that enhances building energy systems. It may improve the heating, ventilation, and air conditioning (HVAC) system performance and ensure it operates correctly to react to changing circumstances instantly (Tarabishy et al., 2021). Furthermore, data from various building systems is integrated via AI-driven building information modelling (BIM) to provide an extensive energy use model. AI-enhanced BIM systems can simulate a building's energy performance in various situations to assist engineers and architects in determining and implementing the best energy-efficient solutions (Awuzie et al., 2024).
AI also makes implementing renewable energy systems within buildings possible. Machine learning algorithms may be used to optimize their location and operation to maximize the efficiency of solar panels, wind turbines, and other renewable energy sources. AI can accurately adjust building energy systems to produce a steady and sustainable supply by estimating energy production from several sources based on weather trends (Osuizugbo et al., 2021).
Furthermore, generative design tools utilize AI algorithms to create building designs that naturally reduce energy consumption. By optimizing natural lighting, ventilation, and insulation, these techniques may provide designs that minimize the need for artificial lighting, heating, and cooling (Chew et al., 2024). Architects can construct structures that are sustainable and energy-efficient for the environment by using AI approaches. Table 2 illustrates how using AI in sustainable architecture has significantly increased energy efficiency in several case studies.
3.3. AI-driven materials selection
Reducing the environmental effects of buildings requires the use of sustainable materials. AI helps significantly with this. AI-powered systems examine massive databases, including information on environmental conditions and material qualities. Next, they recommend the most environmentally friendly choices. These instruments account for material life, recyclable nature, energy use during production, and carbon footprint. This ensures that the materials utilized help the building achieve its sustainability goals. Machines can identify the most environmentally friendly materials and recommend their use in construction projects (Tarabishy et al., 2021).
AI can help engineers and architects identify new materials that improve building performance while being environmentally friendly. AI is also helping to discover new, more sustainable materials. In materials science, AI and machine learning models create materials with specific properties (Awuzie et al., 2024). It can produce materials that require less energy. AI aims to increase the durability of materials to make them environmentally friendly. This innovation in materials science is essential for advancing sustainable architecture and construction practices.
Table 2 AI Techniques for Energy-Efficient Building Design
AI also aids in assessing the lifecycle impact of materials, ensuring that their use aligns with sustainability goals. Osuizugbo et al. (2021) emphasize the importance of lifecycle assessment (LCA) in materials selection, which AI tools can automate and enhance. By assessing materials' environmental effects at every stage of their life cycle, including extraction, manufacture, use, and disposal, artificial intelligence (AI) supports architects in making well-informed decisions that lower the ecological footprint of their designs. In addition to materials selection, AI-driven generative design tools contribute to materials innovation by exploring unconventional materials and construction methods. These resources can recommend more economically and environmentally friendly products and methods (Chew et al., 2024).
3.3.1. AI algorithms and machine learning models
AI and ML have changed the way we approach problemsolving and decision-making. Machine learning (ML) is a topic that focuses on generating and carrying out AI algorithms that can analyze data and its characteristics to decide what to do without the need for explicit programming. In contrast to traditional programming, machine learning algorithms use statistical methods to interpret and learn from data. This enables them to improve and adapt as new data becomes available constantly. The basis of machine learning (ML) is the idea of "learning," which enables algorithms to see patterns, anticipate outcomes, and make sensible decisions. The ML algorithms may be roughly divided into three types: reinforcement learning, unsupervised learning, and supervised learning. Each type of algorithm has a distinct function. These many ML algorithm categories offer a compelling toolset for handling challenging issues, streamlining procedures, and extracting valuable insights from data (Badini et al., 2023). As shown in Fig. 1, they create a complete framework that allows AI systems to evaluate and comprehend data, promoting automation and wise decision-making in various fields.
Figure (1a) shows the schematic representation of the materials design workflow using AI, featuring three key elements: a material dataset, machine learning models that learn and interpret representations for specific tasks, and an output that optimizes and enhances material properties for advanced materials. Figure (1b) is an overview of machine learning methodologies, highlighting the three primary categories: supervised, unsupervised, and reinforcement learning (Frydrych et al., 2021).
3.4. Key studies and findings in this area
Numerous studies show that AI is transforming architectural design and saving time. By optimizing energy consumption and encouraging sustainable materials, artificial intelligence can play an essential role in improving energy and material efficiency performance in the built environment. To meet the challenges of reducing carbon emissions in the built environment, it can emphasize the necessity of ongoing research and development in AI applications (Awuzie et al., 2024).
Osuizugbo et al. (2021) show what experts think about using AI in construction. Their research showed that while people are starting to see the potential of AI, there are still significant challenges. Things like not enough knowledge and resistance to change are holding it back. They conclude that more education and training are needed to utilize AI fully in sustainable architecture. The application of generative design in the built environment shows how AI algorithms can produce creative and sustainable design solutions. These tools can increase creativity and make the design process more efficient, which results in more sustainable buildings. Several case studies demonstrate how AI-driven generative design has produced environmentally sustainable buildings (Chew et al., 2024).
AI can be used to evaluate how the built environment impacts public health. Data from Google Street View and medical records are used to show how AI can offer analysis of the connection between health outcomes and urban design. It emphasizes how important it is for sustainable architecture to take health into account, and in addition, AI-based assessments can identify important urban features that affect public health to support the creation of more health-conscious urban planning and design (Chew et al., 2024).
All of these studies demonstrate how AI has greatly influenced the design of sustainable buildings. They show how AI technology may improve a building's overall quality, sustainability, and efficiency while giving engineers, architects, and urban planners useful new tools. The built environment may be made more robust and sustainable by utilizing AI, which helps solve the urgent issues of urbanization and climate change worldwide.
4. Smart Infrastructure and Urban Planning
4.1. Smart city development
AI plays a crucial role in the development of smart cities by enabling more efficient and sustainable urban planning. Its technologies enable the smooth management of resources and services by facilitating the integration of urban systems. Using artificial intelligence (AI), algorithmic urban planners can analyze huge amounts of data from several urban sectors, including energy, public services, and transportation, to improve city operations and planning (Son et al., 2023). AI's big data processing and analysis capabilities allow city planners to make well-informed decisions based on up-to-date information. In Australia, for example, AI technologies enhance urban planning procedures by predicting urban growth patterns, identifying ideal sites for infrastructure development, and evaluating new projects' environmental impact. This prediction capacity guarantees effective and sustainable urban development, reducing adverse environmental effects and improving locals' living standards (Yigitcanlar et al., 2021). By utilizing AI-based methods, city planners can engage with the community more effectively, gathering input and feedback through digital platforms (Koumetio et al., 2023).
4.2. Traffic and transportation management
Artificial intelligence is changing traffic and transportation management by providing creative ways to reduce traffic, improve security, and promote the general effectiveness of urban mobility systems. Intelligent traffic management system development is one of the significant contributions of AI in this field. The AI-driven traffic control systems can evaluate real-time traffic data gathered from sensors, cameras, and GPS devices to predict traffic jams, improve traffic signal sequences, and provide other routes to vehicles (Nikitas et al., 2020). This real-time adaptability helps reduce traffic jams, lower emissions from idling vehicles, and improve traffic flow in urban areas.
It is also essential to develop smart cars with AI capabilities, advanced sensors, and machine learning algorithms that can facilitate their safe navigation of complicated metropolitan areas. These vehicles may interact with traffic infrastructure to coordinate movements and prevent collisions. AI is also utilized in predictive maintenance, where machine learning models evaluate data from sensors incorporated into roads and bridges to predict maintenance requirements, averting malfunctions and prolonging the life of vital infrastructure (Lv et al., 2020). AI also enhances public transportation systems by improving the efficiency and reliability of services. To guarantee that services are offered where and when most required, AI systems can improve public transportation like bus and train schedules in response to passenger demand patterns (Bharadiya, 2023). Also, by facilitating a quick response from transportation authorities, AI-driven predictive analytics can minimize public transit problems, such as delays. Cities may develop more sustainable urban mobility systems that respond to the demands of their citizens by including AI in traffic and transportation management systems. Figure 2 shows the innovative influence of AI in traffic and transportation management by highlighting major applications that lead to increased sustainability and efficiency in urban environments.
4.3. Water and waste management systems
Artificial intelligence makes waste and water management systems more innovative and sustainable. These AI-powered solutions can predict when maintenance is required. It can monitor water quality and enhance water distribution. To ensure adequate water utilization and minimize waste, AI algorithms are employed to analyze data from sensors installed in water infrastructure (Xiang et al., 2021). By studying garbage formation trends and optimizing collection routes, artificial intelligence (AI) can reduce operating costs and associate negative environmental effects while increasing the efficacy of waste collection and recycling operations in waste management (Reza et al., 2023). AI can also anticipate the effects of catastrophic weather events on waste and water infrastructure. Deep learning's ability to predict floods and other climate-related disasters allows for preventative measures to safeguard infrastructure and guarantee service continuity (Fu et al., 2022). The integration of AI in water and waste management is depicted in Fig. 3, showcasing how these technologies optimize resource usage and enhance environmental sustainability.
4.4. Case studies
Numerous case studies show how effective AI is in innovative infrastructure development and urban planning. Yigitcanlar et al.'s (2021) research offers details on several projects that have improved urban planning procedures using AI; as an example, the City of Melbourne has managed its public transportation system with AI-driven solutions, which has decreased traffic and increased service effectiveness (Yigitcanlar et al., 2020). Singapore's use of AI to manage its water supplies is another noteworthy example. AI technologies have been used to improve water quality and distribution to guarantee that inhabitants have a consistent supply of clean drinking water (Xiang et al., 2021). These AI-driven solutions have significantly reduced costs and improved water management techniques.
Amsterdam has created an AI-based waste management system to optimize garbage collection routes. The initiative's effectiveness resulted in lowering operating expenses and its impact on the environment. By analyzing data on garbage creation trends, the AI system makes it possible to create more effective collection schedules and routes (Reza et al., 2023).
Table 3 contains an overview of several real-world applications of AI in urban planning, highlighting essential case studies that show these technologies' efficacy and influence in enhancing urban environments.
Table 3 Case Studies of AI Applications in Urban Planning
5. Enhancing Building Operations and Maintenance
5.1. Predictive maintenance
AI is changing building maintenance and management to optimize processes, decrease expenses, and increase building system efficiency. AI supports smart grids, predictive maintenance, energy management, and air quality monitoring. AI technologies have a positive impact on building performance.
One effective AI technique for building operations is predictive maintenance, in which building systems may anticipate problems with equipment before they occur by utilizing AI and machine learning techniques. This lowers maintenance costs and delays. Artificial intelligence technologies instantly take information from construction equipment sensors to track conditions. They analyze the data to look for unusual trends and anticipate potential problems. By doing this, maintenance workers can address problems before they occur. This method also increases the life of the equipment and avoids costly failures.
Predictive maintenance systems driven by AI can also manage resources effectively and prioritize tasks for repair according to the equipment's priority. This is particularly important for large commercial buildings where it's necessary to maintain operating efficiency. The accuracy of AI systems' forecasts is predicted to increase as they develop, improving building operations' reliability and effectiveness even more. Figure 4 illustrates how AI is applied in predictive maintenance. It details a comprehensive process where AI enhances maintenance efficiency by using real-time monitoring to detect anomalies and applying predictive analytics to foresee potential issues.
5.2. AI-based energy management systems and smart grids
AI greatly supports building innovative grid development and energy management system advancement. AI-driven energy management systems (EMS) optimize energy use by evaluating data from several sources, including energy pricing, occupancy trends, and weather forecasts. By estimating energy use and appropriately modifying heating, ventilation, and air conditioning (HVAC) systems, these systems may ensure efficient energy usage without reducing comfort (Aguilar et al., 2021).
Facilitating local energy generation and dynamic demand response, like smart grids, which include AI in the energy distribution network, further improves energy efficiency. Real-time energy demand forecasting using AI algorithms is possible, and energy storage devices could be used to balance energy supply from renewable sources like solar panels. This lowers building owners' energy costs and their reliance on fossil fuels. Integrating AI with smart grids, which promote sustainable energy methods, makes integrating electric cars and other energy-consuming equipment into the energy network easier.
5.3. Air quality monitoring and improvement
One of the most critical aspects of ensuring building occupants are comfortable and healthy is indoor air quality, IAQ. AIdriven systems use advanced sensors and machine learning algorithms for IAQ monitoring and improvement to evaluate air quality factors, including humidity, CO2 levels, and organic pollutants (VOCs). AI systems can specify patterns in IAQ data that may not be apparent through manual monitoring to allow for more precise interventions (Verma et al., 2023). AI-based IAQ systems can additionally link with HVAC systems to automatically modify ventilation rates and air purification procedures in response to changes in air quality. This real-time adjustment optimizes energy consumption while maintaining a safe and comfortable home environment. AI can forecast possible problems with air quality based on factors like building occupancy and external pollution levels, which allows preventative action to be taken before IAQ worsens.
5.4. Successful implementations and technologies
Several successful applications in building operations and maintenance have shown the benefits of AI advancements. For example, many commercial and industrial buildings have implemented AI-driven predictive maintenance, significantly lowering maintenance costs and equipment downtime. Case studies show how AI has improved smart building energy use, resulting in significant energy savings and decreased carbon footprints (Fu et al., 2020).
Also, improved accuracy and efficiency in construction management have been made possible by integrating AI with Building Information Modeling and BIM (Rane, 2023). This integration makes better project planning, cost prediction, and quality control possible, resulting in more substantial and sustainable structures. AI technologies are considered to become more widely used in building operations and maintenance as they develop, which is leading to more advancements in occupant well-being, sustainability, and efficiency.
6. Challenges and Limitations
6.1. Technical challenges in AI implementation
Integrating AI into architecture and the built environment presents various technological challenges preventing widespread adoption. One of the most significant challenges is training AI models with diverse data sources. Large amounts of high-quality data are necessary for AI systems to function accurately, especially for those engaged in design creation and predictive modelling. However, gathering such statistics in this field can be difficult because architectural projects are different and sometimes non-standardized. When AI models perform well on training data but cannot generalize to new data, variability can result in overfitting (As et al., 2018). Another technical challenge is the computational power required for AI processes. Deep learning models are essential for developing complicated architectural designs and performing simulations, but they demand significant processing power. This typically results in high prices and energy consumption, which many companies cannot afford. Cloud computing provides a solution, but it also requires enterprises to rely on third-party suppliers, increasing issues about data security and availability (Chaillou, 2020).
Another major problem is the interoperability between AI technologies and current software design. Since many architecture businesses use well-known software like AutoCAD or Revit, it might be challenging to integrate AI features into these programs without interfering with the processes. AI systems must work with current tools to be quickly adopted. Developing APIs and infrastructure to enable this connection is imperative, yet doing so calls for significant financial and technical commitments (Ganin et al., 2021).
6.2. Ethical and private concerns
Deploying AI in architecture and urban planning raises essential ethical and privacy concerns. Large information sets, which may contain sensitive data like building layouts, occupancy patterns, and energy usage statistics, are frequently used by AI systems. There are serious privacy risks linked with the potential use of this data, whether by illegal access or insufficient security measures. These kinds of data can be analyzed to provide insights into the wrong hands that could harm people's and organizations' privacy (Liao et al., 2022). The potential biases in AI systems raise ethical concerns, and these biases can come from the data used to train AI models or from the algorithms themselves. Decisions that harm specific already-existing disparity groups may be made. AI in urban planning could also increase social inequality by giving preference to the requirements of wealthy regions over those of less developed areas. The transparency of AI systems and the ability to review their decision-making procedures to reduce biases must be maintained (Tarabishy et al., 2021). In addition, concerns over the displacement of human labour are raised by the growing dependence on AI in urban planning and architecture. AI systems are beginning to replace human architects and planners in more and more activities, which is raising concerns about job displacement and the need to retrain the workforce.
6.3. Summary of gaps in current research
Even with all of the advancements in AI for architecture and urban planning, there are still significant research gaps. One of the major difficulties is a lack of thorough research into the long-term impacts of employing AI in the built environment. Most recent research has focused on AI-driven designs' immediate benefits and problems rather than the more considerable societal and ecological consequences. This emphasizes the importance of long-term research to understand how AI-generated structures perform over time and how sustainable they are. The lack of research on AI's potential to meet the requirements of developing nations is another gap. Since industrialized nations have more access to the infrastructure and resources needed for AI implementation, most current research is focused on applications in these nations. Further study is required to determine how AI may be adapted to address issues emerging nations confront, like resource shortages and the need for solutions for cheap housing.
Finally, there is a gap in interdisciplinary research that combines AI with other emerging technologies, such as blockchain and the IoT, in the built environment. Also, there is growing interest in these technologies because little is known about their combined potential. According to Chew et al. (2024), investigating the connections between AI and other technologies can produce innovative solutions to the challenging issues related to urban development (Chew et al., 2024).
7. Future Directions and Opportunities
7.1. Emerging AI trends and research opportunities
AI is quickly changing the built environment and introducing new ideas that have the potential to alter the built environment. One trend is combining AI with generative design, which uses algorithms to produce intricate and efficient designs. It isn't easy to investigate several design choices quickly using traditional approaches, but it helps architects and engineers to do so. One example is the development of intelligent generative design methodologies for shear wall constructions using generative adversarial networks. These AI techniques provide innovative and productive designs to save material use and increase sustainability (Liao et al., 2022).
Another significant trend is using AI for real-time environmental analysis and decision-making in urban planning. AI gives tools to evaluate and successfully manage the growing difficulties that metropolitan areas face, from pollution, climate change, and population increase. Urban AI's place in smart cities with a focus on how it may optimize resource management, increase public services, and improve urban residents' quality of life (Luusua et al., 2023). Furthermore, the application of AI-driven carbon-reduction strategies in the built environment is expanding the utilization of AI in enhancing the energy efficiency of materials, which is crucial in achieving sustainability goals (Awuzie et al., 2024). These patterns indicate crucial areas for future study, particularly in merging AI with new technologies such as blockchain and the Internet of Things. There is also an increasing need to investigate the social implications of AI in the built environment, such as its influence on job security, privacy, and justice. As AI advances, academics are motivated to investigate how technology may contribute to creating more resilient, sustainable, and inclusive urban environments.
7.2. Recommendations for future studies
Even though advances in AI for the built environment appear promising, further study is required to realize their full potential. One primary concern is a lack of standards, which may slow down the widespread use of AI technology. Future research should focus on developing standardized frameworks for using AI in built environments (Chaillou, 2020). Architects, engineers, legislators, and software developers can integrate and collaborate more easily if common standards are established. Another critical area for future research is the ethical implications of AI in the built environment. As AI systems become more autonomous, questions surrounding data privacy, surveillance, and algorithmic bias become increasingly pertinent. It is essential to address these worries to avoid AI applications worsening existing social disparities or having unforeseen adverse effects. Researchers must look at ways to reduce these dangers, such as making AI models understandable and ensuring AI systems are built with equity and inclusion.
Furthermore, more multidisciplinary research is required to close the gap between AI technology and human-centred design. This ensures AI improves rather than reduces human well-being, which is essential as technology becomes more incorporated into urban contexts. This involves researching how AI-driven settings affect people individually and in groups on a social and psychological level.
8. Case Studies and Real-World Applications
8.1. Detailed analysis of prominent
Various case studies highlight AI's transformational potential and show how it has been incorporated into practical applications within the built environment. The architecture for COVID-19 analysis is one well-known example. This project uses big data, AI, and sophisticated data architectures to analyze large datasets, which makes it easier to identify and analyze COVID-19 trends in real time. This technology gave immediate and accurate insights into the virus's progress by utilizing AI-powered machine learning algorithms, essential for managing public health and making decisions during the epidemic. The project's success showed AI's vital role in improving crisis management capacities in urban settings, especially in situations that are changing quickly, like global health problems (Alghamdi et al., 2024). Another case study is the Mobility Digital Twin (MDT) initiative, detailed by Wang et al. (2022). This project aimed to digitally recreate metropolitan transportation networks so traffic patterns may be analyzed and monitored in real time. The MDT system constantly modifies urban transportation plans by gathering and analyzing massive volumes of data from IoT devices and AI algorithms. As a result, there is a decrease in improvement in the general effectiveness of urban transportation. The MDT case study is an example of how AI may be used to improve the functioning of urban infrastructure, ultimately improving city people's quality of life.
Another noteworthy case study highlighted AI-powered data processing on cloud-edge coordination for the IoT. The advantages of dividing up computing work between cloud and edge devices are demonstrated by this project, which makes data processing and administration in smart cities more effective. More responsive and adaptable urban services, such as energy distribution and traffic control, are made possible by the AI-driven integration system (Wu, 2020). Wu et al. (2022) investigate the environmental effects of AI in the context of sustainability by using a case study on sustainable AI systems. The focus of this work is on energy-efficient hardware and algorithms as a means of minimizing the environmental effect of AI design and implementation. The research delves deeply into the challenges and prospects for developing AI systems that are both powerful and ecologically sustainable. The findings emphasize the necessity of considering sustainability while developing and implementing AI technology, particularly in metropolitan regions where energy consumption is a significant concern. Finally, a thorough case study on incorporating AI in intelligent building systems can be found in AI-big data analytics for building automation and management systems. The research examines how AI may improve occupant comfort, optimize energy use, and simplify building operations. The system uses machine learning and sophisticated analytics to estimate energy consumption, find ineffectiveness, and make real-time changes (Himeur et al., 2023). This case study highlights how AI can significantly reduce the environmental impact of urban structures while improving their operational effectiveness, supporting the more general objectives of sustainable urban development.
8.2. Success stories and lessons learned
These case studies' practical application of AI provides insightful information and valuable lessons for upcoming initiatives. Alghamdi and colleagues' architecture for COVID19 detection shows how AI can be applied to address public health issues in 2024. The system's capacity to process massive volumes of data in real time and provide insightful analysis is essential to control the pandemic's spread. This case study emphasizes the importance of precise data collection and cautious handling of private health information. Also, it highlights the significance of data systems and moral AI practices while demonstrating how AI might improve crisis response in urban areas. (Alghamdi et al., 2024). Wang et al. (2022) 's transportation The Digital Twin project is a good example of how AI could benefit urban transportation. The MDT system effectively decreased traffic jams and increased transportation effectiveness, highlighting the valuable advantages of AI-driven urban planning. The project's accomplishments highlight how important it is to analyze data in real-time and integrate AI with IoT technology. The MDT case study also highlights the importance of multidisciplinary cooperation between data scientists, engineers, and urban planners to properly utilize AI's potential in urban infrastructure construction.
Another success story is Wu's (2020) cloud-edge orchestration for IoT, which stands out in particular for its capacity to improve the effectiveness of urban services. The effectiveness of hybrid AI techniques in managing complex urban systems is demonstrated by how well the system distributes computing tasks between cloud and edge devices. A key takeaway from this case study is the importance of flexibility in AI system design, which allows for adaptive responses to changing urban environments. This strategy improves urban infrastructure's resilience against problems while improving service delivery. Wu et al. (2022) case study on sustainable AI from 2022 provides valuable details on the environmental effects of AI technology. The experiment showed how AI systems may be made to be both strong and energy-efficient, supporting larger objectives related to sustainability. The necessity of giving sustainability a top priority in AI development is one of the case study's key takeaways, especially in metropolitan settings where energy consumption is a significant problem and needs to be addressed. This includes choosing technology that supports sustainable practices and developing algorithms for energy efficiency.
Research conducted in 2023 by Himeur et al. (2023) on AI-big data analytics in building management systems offers new information on how well AI works to support sustainable urban environments. The project's accomplishments in reducing energy use and raising occupant comfort levels show the valuable advantages of AI in smart buildings. The significance of user-friendly interfaces for building occupants is an essential lesson from this case study. To maximize the advantages of these technologies and meet long-term sustainability goals, it is essential to ensure users are involved and aware of the AI systems in place.
8.3. Impact on sustainability and urban living
These case studies of the effective use of AI offer valuable information and lessons that can direct similar initiatives in the future. The system's ability to process massive amounts of data in real-time and provide insightful analysis was essential to stop the pandemic's spread. Two significant takeaways from this case study are the value of precise data and the ethical management of personal health information. The study also showed how AI might improve urban emergency management while emphasizing the need for robust data architectures and ethical AI methods (Alghamdi et al., 2024).
Global sustainability goals are aligned with the more effective use of transportation resources made possible by the AI-driven MDT system. The project's achievement in lowering pollutants and traffic illustrates AI's potential to build more intelligent, sustainable cities. AI supports the shift to sustainable urban living by increasing the effectiveness and environmental performance of urban transportation systems, which in turn helps to achieve the larger objective of lowering the carbon footprint (Wang et al., 2022). By managing data processing more efficiently, the AI-powered system lowers energy usage and enhances service delivery. This case study illustrates how AI can improve the resilience of city services and optimize resource utilization to assist the development of sustainable urban infrastructure. Effective resource management is essential to achieving sustainability in highly populated metropolitan settings, where the environmental advantages of these systems are most evident (Wu, 2020).
Efficient AI algorithms and sustainable hardware choices, emphasizing that the environmental impact of AI must be considered at every development and deployment stage. This case study illustrates that sustainability in AI is not just about the direct applications of AI in urban environments but also about the underlying technologies that power these systems. By emphasizing sustainable AI development, cities can ensure their technological progress doesn't harm the environment. This approach supports long-term sustainability in urban areas. The notable reduction in energy usage achieved by AI-driven building management systems has improved the overall sustainability of urban infrastructure. These technologies minimize energy usage without sacrificing comfort and improve the quality of life for the building's inhabitants. AI must be integrated into building management to create sustainable urban settings where efficiency and occupant wellbeing are valued.
9. Conclusion
This assessment highlights the substantial advancements in artificial intelligence (AI) that have transformed the built environment. A key finding is AI's application in sustainable building design, enhancing material selection, energy efficiency, and environmental impact evaluations. AI also plays a crucial role in intelligent transportation systems and sustainable urban water management, improving infrastructure development and urban planning. Additionally, AI-driven predictive maintenance extends the lifespan and effectiveness of building systems, fostering more adaptable, resilient, and sustainable urban environments. AI fundamentally changes how cities are designed and managed, facilitating data-driven decision-making to create more sustainable and efficient structures. For example, AI applications in energy management systems have significantly reduced greenhouse gas emissions and energy consumption. Furthermore, advancements in building automation and smart grid technologies enhance infrastructure flexibility, allowing adaptation to changing user demands and environmental conditions. This intersection of AI and sustainability sets new benchmarks for future urban development.
Integrating AI into the built environment represents a paradigm shift with far-reaching implications for academia and industry. AI-driven technologies enable the construction sector to adopt more environmentally friendly practices, providing a competitive edge in a market increasingly focused on sustainability. This transition presents vast opportunities for research and innovation, particularly in environmental science, AI, and urban planning. Developing innovative, sustainable cities depends on cross-sector collaboration, requiring stakeholders to remain adaptable as AI evolves to meet current demands and anticipate future challenges.
Statements and Declarations
Conflicts of interest
The authors of this article declared no conflict of interest regarding the authorship or publication of this article.
Funding
The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.
Data availability
The datasets generated and analyzed during the current study are collected from official organizations in Iran and are available from the corresponding author upon request.
Author contributions
The author conducted the literature review, synthesized the findings, and wrote the manuscript in its entirety.
References
Aguilar, J., Garces-Jimenez, A., R-Moreno, M. D., & García, R. (2021). A systematic literature review on the use of artificial intelligence in energy self-management in smart buildings. Renewable and Sustainable Energy Reviews, 151, 111530. https://doi.org/10.1016/j.rser.2021.111530
Alghamdi, A. M., Al Shehri, W. A., Almalki, J., Jannah, N., & Alsubaei, F. S. (2024). An architecture for COVID-19 analysis and detection using big data, AI, and data architectures. PLoS ONE, 19(8). https://doi.org/10.1371/journal.pone.0305483
As, I., Pal, S., & Basu, P. (2018). Artificial intelligence in architecture: Generating conceptual design via deep learning. International Journal of Architectural Computing, 16(4), 306–327. https://doi.org/10.1177/1478077118800982
Awuzie, B., Ngowi, A., & Aghimien, D. (2024). Towards built environment decarbonisation: A review of the role of artificial intelligence in improving energy and materials’ circularity performance. Energy and Buildings, 319, 114491. https://doi.org/10.1016/j.enbuild.2024.114491
Badini, S., Regondi, S., & Pugliese, R. (2023). Unleashing the power of artificial intelligence in materials design. Materials, 16(17), 5927. https://doi.org/10.3390/ma16175927
Bharadiya, J. (2023). Artificial intelligence in transportation systems: A critical review. American Journal of Computing and Engineering, 6(1), 34–45.
Chaillou, S. (2020, September). Archigan: Artificial intelligence × architecture. In Architectural Intelligence: Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2019) (pp. 117–127). Springer Nature Singapore. https://doi.org/10.1007/978-981-15-6568-7_8
Chen, Z., Dazard, J. E., Khalifa, Y., Motairek, I., Al-Kindi, S., & Rajagopalan, S. (2024). Artificial intelligence–based assessment of built environment from Google Street View and coronary artery disease prevalence. European Heart Journal, 45(17), 1540–1549. https://doi.org/10.1093/eurheartj/ehae158
Chew, Z. X., Wong, J. Y., Tang, Y. H., Yip, C. C., & Maul, T. (2024). Generative design in the built environment. Automation in Construction, 166, 105638. https://doi.org/10.1016/j.autcon.2024.105638
Frydrych, K., Karimi, K., Pecelerowicz, M., Alvarez, R., Dominguez-Gutiérrez, F. J., Rovaris, F., & Papanikolaou, S. (2021). Materials informatics for mechanical deformation: A review of applications and challenges. Materials, 14(19), 5764. https://doi.org/10.3390/ma14195764
Fu, G., Jin, Y., Sun, S., Yuan, Z., & Butler, D. (2022). The role of deep learning in urban water management: A critical review. Water Research, 223, 118973. https://doi.org/10.1016/j.watres.2022.118973
Ganin, Y., Bartunov, S., Li, Y., Keller, E., & Saliceti, S. (2021). Computer-aided design as language. Advances in Neural Information Processing Systems, 34, 5885–5897.
Himeur, Y., Elnour, M., Fadli, F., Meskin, N., Petri, I., Rezgui, Y., & Amira, A. (2023). AI-big data analytics for building automation and management systems: A survey, actual challenges and future perspectives. Artificial Intelligence Review, 56(6), 4929–5021.
https://doi.org/10.1007/s10462-022-10286-2
Koumetio Tekouabou, S. C., Diop, E. B., Azmi, R., & Chenal, J. (2023). Artificial intelligence-based methods for smart and sustainable urban planning: A systematic survey. Archives of Computational Methods in Engineering, 30(2), 1421–1438. https://doi.org/10.1007/s11831-022-09844-2
Liao, W., Huang, Y., Zheng, Z., & Lu, X. (2022). Intelligent generative structural design method for shear wall building based on “fused-text-image-to-image” generative adversarial networks. Expert Systems with Applications, 210, 118530. https://doi.org/10.1016/j.eswa.2022.118530
Luusua, A., Ylipulli, J., Foth, M., & Aurigi, A. (2023). Urban AI: Understanding the emerging role of artificial intelligence in smart cities. AI & Society, 38(3), 1039–1044. https://doi.org/10.1007/s00146-022-01537-5
Lv, Z., Lou, R., & Singh, A. K. (2020). AI-empowered communication systems for intelligent transportation systems. IEEE Transactions on Intelligent Transportation Systems, 22(7), 4579–4587. https://doi.org/10.1109/TITS.2020.3017183
Nikitas, A., Michalakopoulou, K., Njoya, E. T., & Karampatzakis, D. (2020). Artificial intelligence, transport, and the smart city: Definitions and dimensions of a new mobility era. Sustainability, 12(7), 2789. https://doi.org/10.3390/su12072789
Osuizugbo, I. C., & Alabi, A. S. (2021). Built environment professionals' perceptions of the application of artificial intelligence in the construction industry. Covenant Journal of Research in the Built Environment.
Rane, N. (2023). Integrating building information modeling (BIM) and artificial intelligence (AI) for smart construction schedule, cost, quality, and safety management: Challenges and opportunities. Cost, Quality, and Safety Management: Challenges and Opportunities. http://dx.doi.org/10.2139/ssrn.4616055
Reza, M. (2023). AI-driven solutions for enhanced waste management and recycling in urban areas. International Journal of Sustainable Infrastructure for Cities and Societies, 8(2), 1–13.
Son, T. H., Weedon, Z., Yigitcanlar, T., Sanchez, T., Corchado, J. M., & Mehmood, R. (2023). Algorithmic urban planning for smart and sustainable development: Systematic review of the literature. Sustainable Cities and Society, 94, 104562. https://doi.org/10.1016/j.scs.2023.104562
Tarabishy, S., Kosicki, M., & Tsigkari, M. (2021). Artificial intelligence for the built environment. In Industry 4.0 for the Built Environment: Methodologies, Technologies and Skills (pp. 103–130). Springer International Publishing. https://doi.org/10.1007/978-3-030-82430-3_5
Verma, A., Prakash, S., & Kumar, A. (2023). AI-based building management and information system with multi-agent topology for an energy-efficient building: Towards occupants' comfort. IETE Journal of Research, 69(2), 1033–1044. https://doi.org/10.1080/03772063.2020.1847701
Wang, Z., Gupta, R., Han, K., Wang, H., Ganlath, A., Ammar, N., & Tiwari, P. (2022). Mobility digital twin: Concept, architecture, case study, and future challenges. IEEE Internet of Things Journal, 9(18), 17452–17467. https://doi.org/10.1109/JIOT.2022.3156028
Wu, C. J., et al. (2022). Sustainable AI: Environmental implications, challenges, and opportunities. Proceedings of Machine Learning and Systems, 4, 795–813.
Wu, Y. (2020). Cloud-edge orchestration for the Internet of Things: Architecture and AI-powered data processing. IEEE Internet of Things Journal, 8(16), 12792–12805. https://doi.org/10.1109/JIOT.2020.3014845
Xiang, X., Li, Q., Khan, S., & Khalaf, O. I. (2021). Urban water resource management for sustainable environment planning using artificial intelligence techniques. Environmental Impact Assessment Review, 86, 106515. https://doi.org/10.1016/j.eiar.2020.106515
Yigitcanlar, T., Corchado, J. M., Mehmood, R., Li, R. Y. M., Mossberger, K., & Desouza, K. (2021). Responsible urban innovation with local government artificial intelligence (AI): A conceptual framework and research agenda. Journal of Open Innovation: Technology, Market, and Complexity, 7(1), 71. https://doi.org/10.3390/joitmc7010071
Yigitcanlar, T., Desouza, K. C., Butler, L., & Roozkhosh, F. (2020). Contributions and risks of artificial intelligence (AI) in building smarter cities: Insights from a systematic review of the literature. Energies, 13(6), 1473. https://doi.org/10.3390/en13061473
