{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T09:10:36Z","timestamp":1779095436810,"version":"3.51.4"},"reference-count":60,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:00:00Z","timestamp":1771891200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers, Environment and Urban Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.compenvurbsys.2026.102416","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T14:58:29Z","timestamp":1772117909000},"page":"102416","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Fine-grained urban land use simulation: Integrating spatial dynamic modeling with a pre-trained vision-language model"],"prefix":"10.1016","volume":"126","author":[{"given":"Zipan","family":"Cai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Karvonen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Cong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiming","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecolmodel.2021.109685","article-title":"Challenges, tasks, and opportunities in modeling agent-based complex systems","volume":"457","author":"An","year":"2021","journal-title":"Ecological Modelling"},{"issue":"7","key":"10.1016\/j.compenvurbsys.2026.102416_bb0010","first-page":"1243","article-title":"From the street to the metropolitan region: Pedestrian perspective in urban fabric analysis","volume":"46","author":"Araldi","year":"2019","journal-title":"Environment and Planning B: Urban Analytics and City Science"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.landurbplan.2022.104376","article-title":"The place of space in urban metabolism research: Towards a spatial turn? A review and future agenda","volume":"221","author":"Bahers","year":"2022","journal-title":"Landscape and Urban Planning"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0020","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.isprsjprs.2023.05.006","article-title":"Geographic mapping with unsupervised multi-modal representation learning from VHR images and POIs","volume":"201","author":"Bai","year":"2023","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0025","series-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","first-page":"87","article-title":"City foundation models for learning general purpose representations from OpenStreetMap","author":"Balsebre","year":"2024"},{"issue":"3","key":"10.1016\/j.compenvurbsys.2026.102416_bb0030","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1038\/s43588-024-00606-7","article-title":"Digital twins in city planning","volume":"4","author":"Batty","year":"2024","journal-title":"Nature Computational Science"},{"issue":"12","key":"10.1016\/j.compenvurbsys.2026.102416_bb0035","doi-asserted-by":"crossref","first-page":"508","DOI":"10.3390\/urbansci9120508","article-title":"Evolving from rules to learning in urban modeling and planning support systems","volume":"9","author":"Cai","year":"2025","journal-title":"Urban Science"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.ancene.2023.100387","article-title":"Urban spatial dynamic modeling based on urban amenity data to inform smart city planning","volume":"42","author":"Cai","year":"2023","journal-title":"Anthropocene"},{"issue":"8","key":"10.1016\/j.compenvurbsys.2026.102416_bb0045","first-page":"1380","article-title":"Spatial dynamic modelling for urban scenario planning: A case study of Nanjing, China","volume":"47","author":"Cai","year":"2020","journal-title":"Environment and Planning B: Urban Analytics and City Science"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0050","series-title":"The Palgrave Encyclopedia of urban and regional futures","first-page":"1","article-title":"Urban densification and its social sustainability","author":"Cavicchia","year":"2022"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.scs.2020.102486","article-title":"The role of food-energy-water nexus analyses in urban growth models for urban sustainability: A review of synergistic framework","volume":"63","author":"Chang","year":"2020","journal-title":"Sustainable Cities and Society"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0060","series-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"319","article-title":"Profiling urban streets: A semi-supervised prediction model based on street view imagery and spatial topology","author":"Chen","year":"2024"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.cities.2023.104329","article-title":"Automatic assessment of public open spaces using street view imagery","volume":"137","author":"Chen","year":"2023","journal-title":"Cities"},{"issue":"6","key":"10.1016\/j.compenvurbsys.2026.102416_bb0070","doi-asserted-by":"crossref","first-page":"1361","DOI":"10.1109\/JAS.2023.123537","article-title":"Machine learning with data assimilation and uncertainty quantification for dynamical systems: A review","volume":"10","author":"Cheng","year":"2023","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0075","series-title":"Handbook of regional science","first-page":"1751","article-title":"Cellular automata and agent-based models","author":"Clarke","year":"2021"},{"issue":"1\u20132","key":"10.1016\/j.compenvurbsys.2026.102416_bb0080","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.techsoc.2005.10.005","article-title":"Urbanization in developing countries: Current trends, future projections, and key challenges for sustainability","volume":"28","author":"Cohen","year":"2006","journal-title":"Technology in Society"},{"issue":"14","key":"10.1016\/j.compenvurbsys.2026.102416_bb0085","doi-asserted-by":"crossref","first-page":"2013","DOI":"10.1111\/mice.12972","article-title":"Interpretable machine learning learns complex interactions of urban features to understand socio-economic inequality","volume":"38","author":"Fan","year":"2023","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"13","key":"10.1016\/j.compenvurbsys.2026.102416_bb0090","doi-asserted-by":"crossref","first-page":"10682","DOI":"10.3390\/su151310682","article-title":"Sustainalism: An integrated socio-economic-environmental model to address sustainable development and sustainability","volume":"15","author":"Hariram","year":"2023","journal-title":"Sustainability"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.landusepol.2020.104576","article-title":"Exploring the influence of urban form on land-use efficiency from a spatiotemporal heterogeneity perspective: Evidence from 336 Chinese cities","volume":"95","author":"He","year":"2020","journal-title":"Land Use Policy"},{"issue":"4","key":"10.1016\/j.compenvurbsys.2026.102416_bb0100","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1016\/j.compenvurbsys.2003.12.001","article-title":"The role of spatial metrics in the analysis and modeling of urban land use change","volume":"29","author":"Herold","year":"2005","journal-title":"Computers, Environment and Urban Systems"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0105","article-title":"Integrated vision language and foundation model for automated estimation of building lowest floor elevation","author":"Ho","year":"2024","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"5","key":"10.1016\/j.compenvurbsys.2026.102416_bb0110","doi-asserted-by":"crossref","first-page":"1385","DOI":"10.3390\/su11051385","article-title":"Identification of urban functional areas based on POI data: A case study of the Guangzhou economic and technological development zone","volume":"11","author":"Hu","year":"2019","journal-title":"Sustainability"},{"issue":"10","key":"10.1016\/j.compenvurbsys.2026.102416_bb0115","doi-asserted-by":"crossref","first-page":"1905","DOI":"10.1080\/13658816.2022.2040510","article-title":"Estimating urban functional distributions with semantics preserved POI embedding","volume":"36","author":"Huang","year":"2022","journal-title":"International Journal of Geographical Information Science"},{"issue":"7","key":"10.1016\/j.compenvurbsys.2026.102416_bb0120","doi-asserted-by":"crossref","first-page":"1414","DOI":"10.1080\/13658816.2024.2347322","article-title":"Zero-shot urban function inference with street view images through prompting a pretrained vision-language model","volume":"38","author":"Huang","year":"2024","journal-title":"International Journal of Geographical Information Science"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0125","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.isprsjprs.2022.11.021","article-title":"Learning urban region representations with POIs and hierarchical graph infomax","volume":"196","author":"Huang","year":"2023","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"issue":"9","key":"10.1016\/j.compenvurbsys.2026.102416_bb0130","doi-asserted-by":"crossref","first-page":"1849","DOI":"10.1080\/13658816.2025.2543038","article-title":"GeoFM: How will geo-foundation models reshape spatial data science and GeoAI?","volume":"39","author":"Janowicz","year":"2025","journal-title":"International Journal of Geographical Information Science"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0135","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.isprsjprs.2018.02.006","article-title":"Building instance classification using street view images","volume":"145","author":"Kang","year":"2018","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bib292","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s42854-021-00028-y","article-title":"The \u2018New Urban Science\u2019: towards the interdisciplinary and transdisciplinary pursuit of sustainable transformations","volume":"3","author":"Karvonen","year":"2021","journal-title":"Urban transformations"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0140","doi-asserted-by":"crossref","DOI":"10.1016\/j.jclepro.2022.134203","article-title":"Urban resilience and livability performance of European smart cities: A novel machine learning approach","volume":"378","author":"Kutty","year":"2022","journal-title":"Journal of Cleaner Production"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.scitotenv.2020.137149","article-title":"The framework of an agricultural land-use decision support system based on ecological environmental constraints","volume":"717","author":"Li","year":"2020","journal-title":"Science of the Total Environment"},{"issue":"2","key":"10.1016\/j.compenvurbsys.2026.102416_bb0150","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/MGRS.2024.3383473","article-title":"Vision-language models in remote sensing: Current progress and future trends","volume":"12","author":"Li","year":"2024","journal-title":"IEEE Geoscience and Remote Sensing Magazine"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0155","doi-asserted-by":"crossref","first-page":"87713","DOI":"10.1109\/ACCESS.2024.3408843","article-title":"Automatic estimation for visual quality changes of street space via street-view images and multimodal large language models","volume":"12","author":"Liang","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0160","series-title":"ICLR 2023 tiny papers","article-title":"Concept understanding in large language models: An empirical study","author":"Liao","year":"2023"},{"issue":"8","key":"10.1016\/j.compenvurbsys.2026.102416_bb0170","doi-asserted-by":"crossref","first-page":"1675","DOI":"10.1080\/13658816.2017.1324976","article-title":"Classifying urban land use by integrating remote sensing and social media data","volume":"31","author":"Liu","year":"2017","journal-title":"International Journal of Geographical Information Science"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0175","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","article-title":"CLIP4Clip: An empirical study of CLIP for end to end video CLIP retrieval and captioning","volume":"508","author":"Luo","year":"2022","journal-title":"Neurocomputing"},{"issue":"2","key":"10.1016\/j.compenvurbsys.2026.102416_bb0180","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3653070","article-title":"On the opportunities and challenges of foundation models for GeoAI (vision paper)","volume":"10","author":"Mai","year":"2024","journal-title":"ACM Transactions on Spatial Algorithms and Systems"},{"issue":"23","key":"10.1016\/j.compenvurbsys.2026.102416_bb0185","doi-asserted-by":"crossref","first-page":"10255","DOI":"10.3390\/su162310255","article-title":"Forecasting urban land use dynamics through patch-generating land use simulation and Markov chain integration: A multi-scenario predictive framework","volume":"16","author":"Marey","year":"2024","journal-title":"Sustainability"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bib298","series-title":"Land and Water Degradation in Ethiopia: Climate and Land Use Change Implications","first-page":"25","article-title":"Dynamics and predictability of land use\/land cover change using artificial neural network-based cellular automata (ANN-CA): The case of the Upper Awash River Basin, Ethiopia","author":"Meresa","year":"2024"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0190","series-title":"Efficient depth-guided urban view synthesis","first-page":"90","author":"Miao","year":"2025"},{"issue":"1","key":"10.1016\/j.compenvurbsys.2026.102416_bb0195","first-page":"15","article-title":"The social pillar of sustainable development: A literature review and framework for policy analysis","volume":"8","author":"Murphy","year":"2012","journal-title":"Sustainability: Science, Practice and Policy"},{"issue":"6","key":"10.1016\/j.compenvurbsys.2026.102416_bb0200","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1016\/S0198-9715(01)00015-1","article-title":"Using neural networks and GIS to forecast land use changes: A land transformation model","volume":"26","author":"Pijanowski","year":"2002","journal-title":"Computers, Environment and Urban Systems"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bib295","series-title":"Learning transferable visual models from natural language supervision","first-page":"8748","author":"Radford","year":"2021"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0205","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1016\/j.earscirev.2019.01.001","article-title":"Spatially explicit simulation of land use\/land cover changes: Current coverage and future prospects","volume":"190","author":"Ren","year":"2019","journal-title":"Earth-Science Reviews"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0210","series-title":"Accessibility in cities: Transport and urban form","first-page":"239","author":"Rode","year":"2017"},{"issue":"22","key":"10.1016\/j.compenvurbsys.2026.102416_bb0215","doi-asserted-by":"crossref","first-page":"2719","DOI":"10.3390\/rs11222719","article-title":"Urban land use and land cover classification using multisource remote sensing images and social media data","volume":"11","author":"Shi","year":"2019","journal-title":"Remote Sensing"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0220","doi-asserted-by":"crossref","DOI":"10.1016\/j.landusepol.2021.105469","article-title":"Understanding the macro-micro dynamics of urban densification: A case study of different sized Indian cities","volume":"107","author":"Shukla","year":"2021","journal-title":"Land Use Policy"},{"issue":"2","key":"10.1016\/j.compenvurbsys.2026.102416_bb0225","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1177\/0885412211430477","article-title":"Surveying models in urban land studies","volume":"27","author":"Silva","year":"2012","journal-title":"Journal of Planning Literature"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bib293","first-page":"8690","article-title":"Geoclip: Clip-inspired alignment between locations and images for effective worldwide geo-localization","volume":"36","author":"Vivanco Cepeda","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0235","doi-asserted-by":"crossref","DOI":"10.1016\/j.scitotenv.2022.153559","article-title":"Machine learning in modelling land-use and land cover-change (LULCC): Current status, challenges and prospects","volume":"822","author":"Wang","year":"2022","journal-title":"Science of the Total Environment"},{"issue":"1","key":"10.1016\/j.compenvurbsys.2026.102416_bb0240","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1080\/20964471.2020.1810492","article-title":"A review of the use of geosocial media data in agent-based models for studying urban systems","volume":"5","author":"Wen","year":"2021","journal-title":"Big Earth Data"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0245","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.ecoser.2018.02.017","article-title":"The role of socio-economic factors in planning and managing urban ecosystem services","volume":"31","author":"Wilkerson","year":"2018","journal-title":"Ecosystem Services"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.buildenv.2022.109477","article-title":"Generative adversarial networks in the built environment: A comprehensive review of the application of GANs across data types and scales","volume":"223","author":"Wu","year":"2022","journal-title":"Building and Environment"},{"issue":"11","key":"10.1016\/j.compenvurbsys.2026.102416_bb0255","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1080\/13658816.2024.2379468","article-title":"A review of crowdsourced geographic information for land-use and land-cover mapping: Current progress and challenges","volume":"38","author":"Wu","year":"2024","journal-title":"International Journal of Geographical Information Science"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0260","doi-asserted-by":"crossref","DOI":"10.1016\/j.jag.2023.103591","article-title":"Mixed land use measurement and mapping with street view images and spatial context-aware prompts via zero-shot multimodal learning","volume":"125","author":"Wu","year":"2023","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0265","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.landusepol.2018.12.007","article-title":"Bidirectional urban flows in rapidly urbanizing metropolitan areas and their macro and micro impacts on urban growth: A case study of the Yangtze River middle reaches megalopolis, China","volume":"82","author":"Xia","year":"2019","journal-title":"Land Use Policy"},{"issue":"1","key":"10.1016\/j.compenvurbsys.2026.102416_bb0270","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1038\/s41597-023-02844-2","article-title":"Fine-grained urban blue-green-gray landscape dataset for 36 Chinese cities based on deep learning network","volume":"11","author":"Xu","year":"2024","journal-title":"Scientific Data"},{"issue":"11","key":"10.1016\/j.compenvurbsys.2026.102416_bb0275","doi-asserted-by":"crossref","first-page":"2392","DOI":"10.1080\/13658816.2023.2257262","article-title":"Unsupervised land-use change detection using multi-temporal POI embedding","volume":"37","author":"Yao","year":"2023","journal-title":"International Journal of Geographical Information Science"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0280","doi-asserted-by":"crossref","DOI":"10.1016\/j.jag.2021.102514","article-title":"Integrating remote sensing and geospatial big data for urban land use mapping: A review","volume":"103","author":"Yin","year":"2021","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bb0285","first-page":"11789","article-title":"Road network representation learning with the third law of geography","volume":"37","author":"Zhou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.compenvurbsys.2026.102416_bib294","series-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11175","article-title":"Zegclip: Towards adapting clip for zero-shot semantic segmentation","author":"Zhou","year":"2023"}],"container-title":["Computers, Environment and Urban Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0198971526000189?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0198971526000189?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T08:42:02Z","timestamp":1779093722000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0198971526000189"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":60,"alternative-id":["S0198971526000189"],"URL":"https:\/\/doi.org\/10.1016\/j.compenvurbsys.2026.102416","relation":{},"ISSN":["0198-9715"],"issn-type":[{"value":"0198-9715","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Fine-grained urban land use simulation: Integrating spatial dynamic modeling with a pre-trained vision-language model","name":"articletitle","label":"Article Title"},{"value":"Computers, Environment and Urban Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compenvurbsys.2026.102416","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"102416"}}