Urban Economics and Planning

Urban Economics and Planning

Meta-Analysis of Artificial Intelligence Applications in the Development of Mixed Land Uses in Tehran

Document Type : Original Article

Author
Navid Ahangari
Ph.D. in Geography and Urban Planning, Kharazmi University, Tehran, Iran
10.22034/uep.2025.537527.1680
Abstract
Introduction 
In recent decades, the diversification of urban land use has emerged as a key pillar of urban sustainability, as traditional planning models based on segregated land uses have proven inadequate in addressing the complex spatial and social needs of contemporary cities. This inadequacy manifests as spatial fragmentation, weakened social interactions, and increased dependence on motorized transportation. In contrast, development based on mixed land use—emphasizing the coexistence of diverse functions within a shared context—enables improved accessibility and spatial efficiency, reduces energy consumption, strengthens social ties, and enhances infrastructure productivity. However, realizing this approach requires precise and multilayered analyses of the city’s physical, social, and economic structures, which are unattainable without leveraging advanced technologies such as artificial intelligence (AI). AI, through machine learning algorithms, can simultaneously process spatial and social data to identify hidden patterns and complex correlations. This capability enables data-driven urban planning to design targeted and adaptable frameworks for mixed land use, steering urban policies toward resilience and sustainability. Moreover, mixed land use is not merely a physical solution but a multidimensional tool to enhance social, economic, and cultural resilience in urban spaces, reducing vulnerabilities by boosting regional economies and social interactions. Nonetheless, this vision requires accurate spatial data, advanced analytical tools, and institutionalized participatory mechanisms based on data—elements that are often constrained by technical and institutional limitations in many developing cities. Although smart technologies hold high potential for analyzing spatial complexities, their practical application at large scales remains limited and insufficiently responsive to contextual needs. Therefore, bridging the gap between theoretical capacity and practical application demands structural reforms in legal and administrative systems to establish coordinated, participatory, and future-oriented decision-making and to design sustainable, flexible, and resilient land-use patterns. Finally, given Tehran’s demographic and physical challenges, as well as current planning limitations, this research investigates the application of AI in developing mixed land use, with a focus on creating data-driven, multidimensional, and adaptive patterns that address contemporary spatial complexities.
Materials and Methods
This study employs a meta-analytic and systematic review approach to explore the applications of AI in analyzing urban land-use mixtures. It employs path analysis to examine the impact of independent variables on mixed land-use development. In the systematic review phase, using PRISMA software and a three-step process, an extensive search was conducted across reputable databases, including Scopus, SpringerLink, Google Scholar, and Semantic Scholar, resulting in the identification of 2,107 articles. After excluding irrelevant studies and applying stricter inclusion/exclusion criteria, the corpus was reduced to 187 and finally to 65 high-quality articles. Data analysis and visual mapping were conducted using VOSviewer software. In the second phase, seven AI application components were identified as independent variables, and five components of mixed land-use development were designated as dependent variables. Their impacts were examined by a purposive sample of 96 experts and specialists. The questionnaire employed a five-point Likert scale, and data were analyzed using structural equation modeling (SEM) with the partial least squares approach (PLS3). Measurement and structural model analyses were performed via SMARTPLS software, confirming the reliability, validity, and significance of the models.
Findings
Descriptive findings reveal that studies on AI applications in mixed urban land use primarily cluster into three domains: land-use and spatial analysis (29 articles), development strategies and management of mixed use (30 articles), and land-use decision-making (7 articles). Geographically, China leads with 40 articles, followed by the United States (12), Europe (9), and Iran (3), reflecting both the global academic focus and existing gaps in AI application for land-use planning. The temporal trend indicates a sharp increase in publications since 2020, peaking in 2024, underscoring the growing scientific interest in smart technologies for addressing urban planning complexities. Keyword co-occurrence analysis underscores the significance of integrated AI approaches in connecting concepts such as anticipatory planning, demographic shifts, and environmental transformations, thereby playing a crucial role in fostering dynamic and adaptable urban systems. AI techniques, including deep learning, genetic algorithms, ensemble learning, and big data analytics, are widely applied in land-use classification and prediction, spatial layout simulation, and land-use allocation optimization. In SEM analysis, seven AI application components and five mixed land-use development components were identified, with measurement models exhibiting factor loadings above 0.4 and acceptable reliability and validity. Structural model fit indices (GoF = 0.739, R² = 0.716, Q² = 0.506) indicate strong explanatory power and predictive accuracy. All paths between independent and dependent variables were significant at the 95% confidence level. The most influential factors were spatial layout modeling and simulation, stakeholder participation and negotiation modeling, and synergy among intelligent algorithms. Other significant paths included land-use prediction and classification, overall AI application, data fusion and ensemble learning, big data and urban trends analysis, and land-use allocation optimization—collectively demonstrating AI’s critical role in enhancing mixed urban land use.
Conclusion
Artificial intelligence, through advanced analysis and integration of geographic, social, and environmental data, has created significant capacities for understanding and managing the complexities of mixed urban land uses. Systematic review findings indicate that AI applications are concentrated in spatial and land-use analysis, development strategies, and urban planning decision-making, with notable growth since 2020. Keyword co-occurrence reveals AI as a transformative agent linking environmental, demographic, and anticipatory planning concepts, enabling the transition from traditional to dynamic and forward-looking models. Advanced AI techniques, leveraging multi-source data such as satellite imagery, transportation data, and social networks, have played essential roles in land-use classification, optimization, and simulation, enhancing urban system resilience to environmental and social challenges. Research highlights the importance of socio-cultural dimensions, transparent governance, and algorithmic fairness, advocating for ethical frameworks and interdisciplinary collaboration. Technological constraints, including high computational demands and data challenges, underscore the need for cloud computing and federated learning solutions. Structural equation modeling confirms significant effects of AI components on mixed land-use development in Tehran, notably spatial layout modeling, participatory decision-making facilitation, and intelligent algorithm integration. Overall, AI offers an efficient platform for modeling, prediction, participation, and optimization, substantially improving decision quality and sustainable mixed land-use development in Tehran, while future research must focus on advancing technical infrastructure, ensuring algorithmic justice, and fostering interdisciplinary collaboration.
Keywords
Artificial Intelligence
Meta-Analysis
Mixed Land Uses
Sustainable Development
Tehran

Subjects

AlKhereibi, A. H., Wakjira, T. G., Kucukvar, M., and Onat, N. C. (2023). Predictive machine learning algorithms for metro ridership based on urban land use policies in support of transit-oriented development. Sustainability, 15(2), 1718. https://doi.org/10.3390/su15021718.
Alshari, E. A., Abdulkareem, M. B., and Gawali, B. W. (2023). Classification of land use/land cover using artificial intelligence (ANN-RF). Frontiers in Artificial Intelligence, 5, Article 964279. https://doi.org/10.3389/frai.2022.964279.
Anwar, M. R., and Sakti, L. D. (2024). Integrating Artificial Intelligence and Environmental Science for Sustainable Urban Planning. IAIC Transactions on Sustainable Digital Innovation (ITSDI). https://doi.org/10.34306/itsdi.v5i2.666.
Borhani, M., and Ghasemloo, N. (2020). Soft computing modelling of urban evolution: Tehran metropolis. International Journal of Interactive Multimedia and Artificial Intelligence, 6(1), 7–15. https://doi.org/10.9781/IJIMAI.2019.03.001.
Castro, M. L., Machado, P., Santos, I., Rodriguez-Fernandez, N., Torrente-Patiño, A., and Carballal, A. (2022). State of the art on artificial intelligence in land use simulation. Journal of Advanced Transportation, 2022, Article ID 2291508. https://doi.org/10.1155/2022/2291508.
Chaturvedi, V., and de Vries, W. T. (2021). Machine learning algorithms for urban land use planning: A review. Urban Science, 5(3), 68. https://doi.org/10.3390/urbansci5030068.
Chen, B., Tu, Y., Song, Y., Theobald, D. M., Zhang, T., Ren, Z., Li, X., Yang, J., Wang, J., Wang, X., Gong, P., Bai, Y., and Xu, B. (2021). Mapping essential urban land use categories with open big data: Results for five metropolitan areas in the United States of America. ISPRS Journal of Photogrammetry and Remote Sensing, 178, 203–218. https://doi.org/10.1016/j.isprsjprs.2021.06.010.
Chen, R., Yi, X., Zhao, J., He, Y., Chen, B., Liu, F., Yao, X., Jiang, X., Lian, Z., and Li, H. (2025). AI for landscape planning: Assessing surrounding contextual impact on GAN-generated green land layouts. Cities, 166, 106181. https://doi.org/10.1016/j.cities.2025.106181.
Chen, W., Zhao, L., Kang, Q., and Di, F. (2020). Systematizing heterogeneous expert knowledge, scenarios and goals via a goal-reasoning artificial intelligence agent for democratic urban land use planning. Cities, 101, 102703. https://doi.org/10.1016/j.cities.2020.102703.
Cheshmehzangi, A., and Li, H. M. A. (2020). Innovation through urban diversity and achieving comprehensive sustainable urbanism from a community-oriented approach. Current Urban Studies, 8(2), 222–240. https://doi.org/10.4236/cus.2020.82012.
 Crosas, C., Gómez-Escoda, E., and Villavieja, E. (2024). Interplay between land use planning and functional mix dimensions: An assemblage approach for Metropolitan Barcelona. Sustainability, 16(17), 7734. https://doi.org/10.3390/su16177734.
Ghasemi, K. (2024). Enhancing urban livability: Analyzing Tehran through equitable land use distribution. Journal of Urban Management. https://doi.org/10.1016/j.jum.2024.06.005.
Goodspeed, R. (2020). Smart cities: Moving beyond urban cybernetics to tackle wicked problems. Cambridge Journal of Regions, Economy and Society, 13(1), 95–112. https://doi.org/10.1093/cjres/rsz023
Görgün, E. K., and Çubukçu, K. (2022). Mixed land-use and measuring diversity of land-use. Ege Coğrafya Dergisi. https://doi.org/10.51800/ecd.1014773.
Hadiyana, T., and Ji-hoon, S. (2024). AI-driven urban planning: Enhancing efficiency and sustainability in smart cities. ITEJ (Information Technology Engineering Journals), 9(2). https://doi.org/10.24235/itej.v9i2.124.
Hair, J. F., Jr., Hult, G. T. M., Ringle, C. M., and Sarstedt, M. (2022). A primer on partial least squares structural equation modeling (PLS-SEM). Springer. https://doi.org/10.1007/978-3-030-80519-7.
Hara, Y., Hiramatsu, A., Honda, R., Sekiyama, M., and Matsuda, H. (2010). Mixed land-use planning on the periphery of large Asian cities: The case of Nonthaburi Province, Thailand. Sustainability Science, 5(2), 237–248. https://doi.org/10.1007/s11625-010-0104-2.
He, X. (2022). Energy effect of urban diversity: An empirical study from a land-use perspective. Energy Economics, 109, 105892. https://doi.org/10.1016/j.eneco.2022.105892.
Jinollo, G. T., Workalemahu, L., and Adugna, D. (2024). Impact assessment of mixed land-use planning in Ethiopia: The case of Addis Ababa. Heliyon, 10, e40814. https://doi.org/10.1016/j.heliyon.2024.e40814.
Kasahun, M., and Legesse, A. (2024). Machine learning for urban land use/cover mapping: Comparison of artificial neural network, random forest and support vector machine, a case study of Dilla town. Heliyon, 10(20), e39146. https://doi.org/10.1016/j.heliyon.2024.e39146.
Koumetio Tekouabou, S. C., Diop, E. B., Azmi, R., and 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.
Lebedeva, O. (2024). Study of characteristics of mixed land use in the urban environment. Bulletin of the Angarsk State Technical University, 1(18), 257–261. https://doi.org/10.36629/2686-777x-2024-1-18-257-261.
Lee, S., and Lee, M. (2021). A study of establishment and application algorithm of artificial intelligence training data on land use/cover using aerial photograph and satellite images. Korean Journal of Remote Sensing, 37(5_1), 871–884. https://doi.org/10.1234/xyz1234/
Li, J., and Zhu, Y. (2024). An AI-based method for identifying urban land use types based on areas of interest (AOI) and multi-source data. Land, 13(2), Article 2040. https://doi.org/10.xxxx/land1302040.
Lyu, X., Han, Q., and de Vries, B. (2022). A hypothetical urban layout generation model for exploring land use impacts on travel behavior. Travel Behaviour and Society, 28, 317–329. https://doi.org/10.1016/j.tbs.2022.04.009.
Masoumi, Z., and van Genderen, J. (2023). Artificial intelligence for sustainable development of smart cities and urban land-use management. Geo-spatial Information Science, 27(4), 1212–1236. https://doi.org/10.1080/10095020.2023.2184729.
Mirzahosein, H., Zamani, A., and Hajiseyedrazi, N. S. (2021). Review of applications of machine learning and agent-based methods in land use planning. Surveying Sciences and Techniques, 11(2), 129–152. http://jgst.issgeac.ir/article-1-1017-fa.html [In Persian].
Meshkini, A., Rabani, T., Eftekhari, R., and Rafiei, M. (2019). Futures studies of governance: Expanding the concept and future of metropolitan governance in Tehran. Urban Planning Geographical Research, 7(3), 431–453. https://doi.org/10.22059/jurbangeo.2019.241191.778 [In Persian].
Motieyan, H., and Azmoodeh, M. (2021). Mixed-use distribution index: A novel bilevel measure to address urban land-use mix pattern (A case study in Tehran, Iran). Land Use Policy. https://doi.org/10.1016/j.landusepol.2021.105724.
Nekkanti, H., Dey, S., and Chimakurthi, H. M. C. (2025). Integration of geospatial techniques and machine learning in land parcel prediction. Geosystems and Geoenvironment, 4(2), 100371. https://doi.org/10.1016/j.geogeo.2025.100371.
Ramiana, C. N., Widiastuti, R., and Harsritanto, B. I. R. (2017). Implementing Mixed Land Use: Rooting Jane Jacobs’ Concept of Diversity in Urban Sustainability. Majalah Ilmiah Globe, 17(1), 27–35. https://doi.org/10.14710/mdl.17.1.2017.27-35
Sadidi, J., Tamnia, F., and Rezaian, H. (2024). Evaluation of artificial intelligence use in completing volunteered geographic information data: Case study of OSM land use data. Environmental Hazards Spatial Analysis, 11(1), 1–15. http://jsaeh.khu.ac.ir/article-1-3398-fa.html [In Persian].
Tayebi, S., Alavi, S., Esfandi, S., Meshkani, L., and Shamsipour, A. (2023). Evaluation of land use efficiency in Tehran’s expansion between 1986 and 2021: Developing an assessment framework using DEMATEL and interpretive structural modeling methods. Sustainability, 15(4), 3824. https://doi.org/10.3390/su15043824.
Wang, D., Fu, Y., Liu, K., Chen, F., Wang, P., and Lu, C. T. (2023). Automated urban planning for Reimagining City configuration via adversarial learning: Quantification, generation, and evaluation. ACM Transactions on Spatial Algorithms and Systems, 9(1). https://doi.org/10.1145/3524302.
Wang, J., Bretz, M., Dewan, M. A. A., and Aghajani Delavar, M. (2022). Machine learning in modelling land-use and land cover-change (LULCC): Current status, challenges and prospects. Science of The Total Environment, 822, 153559. https://doi.org/10.1016/j.scitotenv.2022.153559.
 Wang, T., and Yorke-Smith, N. (2025). Introduction: AI for and in urban planning. Urban Planning. https://doi.org/10.17645/up.9417.
Wu, X., Liu, X., Zhang, D., Zhang, J., He, J., and Xu, X. (2022). Simulating mixed land-use change under multi-label concept by integrating a convolutional neural network and cellular automata: A case study of Huizhou, China. GIScience and Remote Sensing, 59, 609–632. https://doi.org/10.1080/15481603.2022.2049493.
Yu, Y., Cao, Y., Hou, D., Disse, M., Brieden, A., Zhang, H., and Yu, R. (2022). The study of artificial intelligence for predicting land use changes in an arid ecosystem. Journal of Geographical Sciences, 32, 717–734. https://doi.org/10.1007/s11442-022-1969-6.
Urban Economics and Planning
Volume 6, Issue 4
Winter 2026
Pages 176-191

  • Receive Date 28 July 2025
  • Revise Date 26 August 2025
  • Accept Date 18 September 2025