AI-Powered Digital Twins for the Cities of Tomorrow
An internship in GATE can be organised
Suggested elective: 3D modelling for City Digital Twins based on geospatial information
Tips: Watch the recordings to get an idea of the output we produced recently with students:
Session1:https://lnkd.in/eRBkyfTt
Session2: https://lnkd.in/ezefMFdc
Generative AI and Digital Twins (DTs) are redefining how urban environments are conceptualized, designed, and managed. This research topic explores the development of an intelligent, web-based 3D interface where users can place and configure new buildings within a realistic digital model of a neighbourhood, district, or city. By integrating geospatial, remote sensing, regulatory, and construction permit datasets, the system automatically generates optimal building configurations and evaluates their environmental, spatial, and social impacts. Large Language Models (LLMs) enrich this process by interpreting regulations, assessing compliance, and providing clear, evidence-based guidance to support planning and design decisions.
The student will explore how AI-driven insights, automated regulatory reasoning, and interactive 3D environments can enhance collaboration between planners, designers, policymakers, and citizens. The overarching aim is to contribute to next-generation digital twin systems that help cities become more sustainable, transparent, adaptable, and inclusive.
The topic can be a collaboration with the GATE institute in Bulgaria (Sofia), with a possible case study in Sofia, Amsterdam or Utrecht.
Objectives:
The project aims to create an intelligent Digital Twin environment that integrates urban data, automates building configuration, checks regulatory compliance using LLMs, and evaluates environmental and spatial impacts to support better planning decisions.
Methodology:
The work will integrate multi-source datasets into a unified 3D model, apply AI and LLM-based reasoning for scenario evaluation and compliance checking, and test the prototype through case studies to assess performance and usefulness.
References:
- https://arxiv.org/abs/2406.12360
- https://arxiv.org/abs/2505.08833
- https://arxiv.org/abs/2505.24260
- https://www.researchgate.net/publication/389986165_LLM_Planning_Agents_Exploring_the_potential_and_challenges_of_large_language_model_agents_in_urban_design_and_planning
- https://arxiv.org/abs/2402.01698
- https://www.researchgate.net/publication/389986165_LLM_Planning_Agents_Exploring_the_potential_and_challenges_of_large_language_model_agents_in_urban_design_and_planning
- https://www.ibm.com/think/topics/agentic-ai-vs-generative-ai?utm_source=chatgpt.com
- https://medium.com/urban-ai/the-power-of-generative-ai-in-urban-planning-text2map-revolution-38544f02fb29
- https://medium.com/urban-ai/ai-agents-in-urban-planning-a-new-paradigm-for-urban-simulation-41c4c210e4a8
- https://link.springer.com/article/10.1007/s44212-024-00060-w
Additional references
- Cárdenas, I., Koeva, M., Davey, C. & Nourian, P., (2024). Urban digital twin-based solution using geospatial information for solid waste management, Sustainable Cities and society
- Campoverde C, Koeva M, Persello C, Maslov K, Jiao W, Petrova-Antonova D. Automatic Building Roof Plane Extraction in Urban Environments for 3D City Modelling Using Remote Sensing Data. Remote Sensing. (2024); 16(8):1386. https://doi.org/10.3390/rs16081386
- Cárdenas, I., Koeva, M., Davey, C. & Nourian, P., (2024). Solid Waste in the Virtual World: A Digital Twinning Approach for Waste Collection Planning. Springer, p. 61-74 (Lecture Notes in Geoinformation and Cartography; vol. XIII).
- La Guardia, M. , & Koeva, M. N. (2023). Towards Digital Twinning on the Web: Heterogeneous 3D Data Fusion Based on Open-Source Structure. Remote sensing, 15(3), Article 721. Advance online publication. https://doi.org/10.3390/rs15030721
- de Vries, J., Atun, F., & Koeva, M. N. (2023). Analysis of Potential Disruptions from Earthquakes in Istanbul and 3D Model Based Risk Communication. IDRiM Journal, 13(2), 60-89.
- Kumalasari, D. , Koeva, M. , Vahdatikhaki, F., Petrova Antonova, D. , & Kuffer, M. (2023). Planning walkable cities: Generative design approach towards digital twin implementation. Remote sensing, 15(4), Article 1088. https://doi.org/10.3390/rs15041088
- Cárdenas, I. L., Morales, R., Koeva, M., Atun, F., & Pfeffer, K. (2023, Aug 31). Digital Twins for Physiological Equivalent Temperature Calculation Guide. Zenodo. https://doi.org/10.5281/ZENODO.8306456
- Hu, C., Fan, W., Zeng, E., Hang, Z., Wang, F., Qi, L., & Bhuiyan, M. Z. A. (2021). Digital twin-assisted real-time traffic data prediction method for 5G-enabled internet of vehicles. IEEE Transactions on Industrial Informatics, 18(4), 2811-2819.
- Z. Wang et al., "Mobility Digital Twin: Concept, Architecture, Case Study, and Future Challenges," in IEEE Internet of Things Journal, vol. 9, no. 18, pp. 17452-17467, 15 Sept.15, 2022, doi: 10.1109/JIOT.2022.3156028.
- La Guardia, M., Koeva, M., D'Ippolito, F., & Karam, S. (2022). 3D DATA INTEGRATION FOR WEB BASED OPEN SOURCE WebGL INTERACTIVE VISUALISATION. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences.
- Lehtola, V. V., Koeva, M., Elberink, S. O., Raposo, P., Virtanen, J. P., Vahdatikhaki, F., & Borsci, S. (2022). Digital twin of a city: Review of technology serving city needs. International Journal of Applied Earth Observation and Geoinformation, 102915.
- Khawte, S. S., Koeva, M. N., Gevaert, C. M., Oude Elberink, S., & Pedro, A. A. (2022). DIGITAL TWIN CREATION FOR SLUMS IN BRAZIL BASED ON UAV DATA. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences.
- Ying, Y., Koeva, M., Kuffer, M., & Zevenbergen, J. (2022). Toward 3D Property Valuation—A Review of Urban 3D Modelling Methods for Digital Twin Creation. ISPRS International Journal of Geo-Information, 12(1), 2.
- de Vries, J., Atun, F., & Koeva, M. N. (2022). ASSESSING POTENTIAL DISRUPTIONS FROM EARTHQUAKES IN THE HISTORICAL PENINSULA IN ISTANBUL USING 3D MODELLING. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences.
- Grift, J., Persello, C., Koeva ,M., (2024). CadastreVision: A benchmark dataset for cadastral boundary delineation from multi-resolution earth observation images. ISPRS Journal of Photogrammetry and Remote Sensing, Volume 217, Pages 91-100, https://doi.org/10.1016/j.isprsjprs.2024.08.005.
- Metaferia, M. T., Bennett, R. M., Alemie, B. K., & Koeva, M. (2023). Furthering Automatic Feature Extraction for Fit-for-Purpose Cadastral Updating: Cases from Peri-Urban Addis Ababa, Ethiopia. Remote Sensing, 15(17), 4155.
- Ahsan, M. S., Hussain, E., Ali, Z., Zevenbergen, J., Atif, S., Koeva, M., & Waheed, A. (2023). Assessing the Status and Challenges of Urban Land Administration Systems Using Framework for Effective Land Administration (FELA): A Case Study in Pakistan. Land, 12(8), 1560.
Projects: https://sites.google.com/view/milakoeva/projects
Recent recordings:
Session1:https://lnkd.in/eRBkyfTtSession2: https://lnkd.in/ezefMFdc
Talks: https://www.utwente.nl/en/digital-society/research/digitalisation/digital-twin-geohub/talks/
Research: https://www.utwente.nl/en/digital-society/research/digitalisation/digital-twin-geohub/research/msc-thesis/
The topic is suitable for Spatial Engineering students since it is multidisciplinary and is focused on wicked problems.