Thursday, October 09, 2025

Call for Papers: Geosimulation and Its Emerging Directions with AI




As part of the GeoAI and Deep Learning Symposium at the 2026 AAG Annual Meeting in San Francisco, California we have a call for papers for sessions entitled "Geosimulation and Its Emerging Directions with AI"

Call for Papers:

Simulating past, present, and future events can empower humans to understand the composition and interactions in complex systems and explain their emergence and evolution from bottom up. In practice, geosimulations constitute a powerful tool in engaging different stakeholders, exploring what-if scenarios, and evaluating alternative policy outcomes.

We invite interdisciplinary works for the exploration and understanding of complex social and environmental processes by means of computer simulation. We focus on all aspects of simulation and agent societies, including multi-agent systems, agent-based modeling, microsimulation, artificial intelligence (AI) agents, and the integration of Generative AI with simulation.

As GenAI is impacting all aspects of our lives, we are wondering how it will impact geospatial simulations. How do multimodal large language models (MLLMs) help with agent-decision making in the form of generating agent-personas or scheduling agent activities? Can MLLMs reduce coding barriers for beginners? Will GenAI lead to a new generation of modeling toolkits? What are the challenges brought by MLLMs in model design, validation, and computing costs?

We welcome a wide range of studies exploring simulation theories, data, methodologies, and frameworks. We are also interested in case studies applying geosimulations to address real-world challenges. Potential topic areas include, but are not limited to:
  • Geosimulation Models and Applications
  • Conceptual Geosimulation Models
  • General-Purpose Geosimulation Framework
  • AI and Geosimulation
  • Agents’ Behaviors, Decision-making and AI Agents
  • Data Generation Framework
  • Validation and Verification for Geosimulation
  • Digital Twins
  • Microsimulation
  • Multi-agent Systems

If you are interested, please email your title and 250-word abstract to Fuzhen Yin (fyin@uccs.edu) and Jeon-Young Kang (geokang@khu.ac.kr) by October 30th.

Chairs:

Organizers:
Sponsor Groups:

Friday, August 01, 2025

LLMs and ABMs

In a previous post we talked about the potential of Generative AI for urban modeling, keeping with this theme at the 11th International Conference on Computational Social Science (IC2S2), Na Jiang, Boyu Wang and myself had a poster entitled  Agent-based Models with Large Language Models: Two Modeling Examples. 

In this poster and extended abstract we detail how LLMs can help with many aspects of agent-based modeling development. If this sounds of interest, below you can see the abstract, the poster and the full referece and link to the extended abstract .

Abstract:

Large language models (LLMs) play an important role in AI-powered code assistants such as code completion, debugging, and documentation. Such models can be further fine-tuned on smaller amount of data for specific tasks, often with the improvement of performance compared to generic LLMs. However, such fine-tuning techniques are seldomly used in generating sophisticated agent-based models (ABMs), because they are often implemented as software that demands extra standards such as the Overview, Design concepts, and Details (ODD) protocol. This research examines how we can bridge this gap by utilizing LLMs in designing or conceptualizing, building, and running agent-based models in the form of user prompts. In this work, two models are created to demonstrate the proposed method. Specifically, Sakoda's checkerboard model of social interaction is created by LLM from explicit design and description through prompts. The other model stimulates consumer preferences and restaurant visits as designed and implemented by a LLM. These models are evaluated by human experts on their code correctness and quality for both verification and validation purposes. This work serves as a first step towards fine-tuned LLMs on existing models and documentations to create high-quality and functional ABMs based on either user prompts or standard protocols, contributing to further exploration on the future of AI-assisted geospatial simulation development.

Keywords: agent-based modeling, geospatial simulations, large language models, generative AI, coding 


Full reference: 

Jiang, N., Wang, B. and Crooks, A.T. (2025), Agent-based Models with Large Language Models: Two Modeling Examples, 11th International Conference on Computational Social Science (IC2S2), 21-24th July, Norrkoping, Sweden. (extended abstract pdf) (poster pdf)

Friday, July 18, 2025

Examining spatial expansion and stemming strategies of urban shrinkage

In the past we have written about how one can study urban shrinkage with a specific emphasis on Detroit from both an agent-based modeling perspective and also from analyzing newspapers through natural language processing  Keeping with the theme of Detroit and urban shrinkage we (Xiaoliang Meng, Yichun Xie, Junyi Wu, Heather Khan Welsh,  Shi Zeng and myself) have a new paper entitled "Examining spatial expansion and stemming strategies of urban shrinkage: evidence from Detroit, USA" which was recently published in npj Urban Sustainability

In this paper we introduce a method for studying urban shrinkage by constructing multi-scale spatial structures based on urban network connectivity which we call gravity-networked spatial interaction zones-based spatial panel modeling or GSIZs-Spanel for short. We demonstrate this method by exploring the spatial processes and scopes of past urban shrinkage in Detroit between 2000 and 2020.  If this sounds of interest, below you can read the abstract to the paper, along with the conceptual design of GSIZs-Spanel modeling framework and some of our results. While at the bottom of the post you can find the full referece and link to the paper. 

Abstract:

This study introduces a new modeling paradigm called gravity-networked spatial interaction zones-based spatial panel modeling (GSIZs-Spanel). Using Detroit as a case study, this paper investigates urban shrinkage by integrating shrinkage driving factors, their regional interactions, networks of cities, spatial processes, and longitudinal dynamics. Results suggest that high minority population concentration and persistent poverty are the primary factors impacting Detroit’s inner-city shrinkage. Demographics, economics, and development practices affect shrinkage in suburbs and surrounding cities. Shrinkage spreads outwards like waves; different juxtapositions of driving factors affect shrinkage resilience; spillover effects are particularly vibrant at 25–50 GSIZs; rightsizing is a rational strategy, but it failed to work alone. Integrating spatial planning of driving factors, land uses, spillover effects, rightsizing strategy, and regional collaboration among federal, regional, and local organizations could moderate urban decline. GSIZs-Spanel, which was developed here, could be applied in any U.S. city or other global city.

The conceptual design of GSIZs-Spanel modeling framework.
Patterns of spillover effects of the Spanel models at the 5-incremental spatial clusters. (a: Spatial processes of urban shrinkage. b: Spatial patterns of vacancy severity.)

Spillover effects of the Spanel models at the 5-incremental spatial clusters

Full Reference: 

Meng X., Xie, Y., Crooks, A.T., Wu J., Khan-Welsh, H. and Zen, S. (2025), Examining spatial expansion and stemming strategies of urban shrinkage: evidence from Detroit, USA, npj Urban Sustainability, 5: 52. Available at https://doi.org/10.1038/s42949-025-00245-5 (pdf)

Saturday, July 05, 2025

New Editorial: Generative AI and Urban Modeling

In the current issue of Environment and Planning B, we (Boyu WangNa Jiang and myself) have a new editorial entitled "Generative AI and Urban Modeling". The premise of this editorial is that Generative AI (GenAI) is impacting all aspects of our daily lives and as such has we were wondering how will it impact urban modeling? 

For example, in the editorial we discuss how  GenAI could speed up the overall urban modeling process. To demonstrate this we show how ChatGPT (and its built-in coding interface Canvas) can take published papers and build agent-based models from them (one being of an abstract space and another being spatially explicit). 

However, while model building is time consuming task, another challenge modelers face is how to incorporate decision making within them. To this end we also discuss how large language models (LLMs) have the potential to help with  agent-decision making in the form of generating  agent-personas or scheduling agent activities. 

We conclude the editorial with a series of questions: how will GenAI impact urban modeling? Will it open up the field to more people without the need for strong coding skills? Will we see growth in using LLMs for generating behavior? Will GenAI lead to a new generation of modeling toolkits? While these are only a short list of questions, they also raise concerns that relate back to some of the more thorny issues of urban modeling, that of verification and validation. 

If this sounds of interest you can read the full editorial here

Full Referece: 

Crooks, A.T., Jiang, N. and Wang, B. (2025), Generative AI and Urban Modeling, Environment and Planning B, 52(6), 1277-1281. (pdf)

Monday, June 30, 2025

CUPUM 2025

I have just gotten back from attending the 19th International Conference on Computational Urban Planning and Urban Management (CUPUM) in London and thought I would  share the two papers we presented at the conference. 

The first paper was with Qingqing Chen and Linda See and was entitled "Using New Sources of Data for Urban Climate Modeling Generated through MLLMs on Street View Imagery. "As the title might suggest, this paper was about how one can leverage multi-modal large language models (MLLMs) to extract information on building height, age and function from street level photographs. We demonstrate this using street view images from Mapillary and than ask ChatGPT to estimate the building height, age and function and compare the results to authoritative data sources. If this sounds of interest, below you can see the abstract to the paper, some if the figures (i.e., the work flow and prompts) while the results can be seen in the attached paper (see the link below).

Abstract:

Urban climate and energy balance models require data on the form and function of buildings, but high resolution spatially explicit data sets are often lacking. Here we demonstrate how multi-modal large language models (MLLMs) can be used to extract information on building height, age and function from street level photographs for New York City. A workflow is presented that illustrates the approach, with initial results indicating that the building function can be identified with good accuracy while moderate accuracies were obtained for building heights and age. Suggestions for how to improve these accuracies are also provided. 

KEYWORDS: Buildings, ChatGPT, Multi-modal Large Language Models (MLLMs), Mapillary, Street View Images (SVI).

An overview of research workflow.

The detailed description of multi-step prompting and an example of extracted building attributes information.

Full Reference:

Chen, Q., See, L. and Crooks, A.T. (2025), Using New Sources of Data for Urban Climate Modeling Generated through MLLMs on Street View Imagery. In Cramer-Greenbaum, S., Dennett, A., and Zhong, C (eds.), Proceedings of the 19th International Conference on Computational Urban Planning and Urban Management (CUPUM), London, UK. (pdf)




We then moved back to agent-based modeling with a paper with entitled "Enhancing Spatial Reasoning and Behavior in Urban ABMs with Large-Language Models and Geospatial Foundation Models" which brought back together Nick Malleson, Alison Heppenstall, Ed Manley and myself. In this paper we discuss the potential role of LLMs and geospatial foundation models in the context of agent-based modeling. If this sounds of interest, below you can read the abstract to the paper and find a link to it at the bottom of the post. Nick has also shared the slides of this presentation here

Abstract: 
Modeling human behavior continues to be a significant challenge for the field of agent-based modeling, and one that prohibits the development of comprehensive empirical ABMs for urban applications, such as Urban Digital Twins. However, two recent methodological advances offer the potential to transform empirical agent-based models.

Early evidence suggests that large-language models (LLMs) can be used to represent a wide range of human behaviors, with models responding in realistic ways to given prompts. Indeed there is already a flurry of activity that focusses on implementing LLM-backed agents -- i.e. agents who are controlled by LLMs. At the same time, the concept of the foundation model is also being applied in domains beyond text analysis. Of particular interest are geospatial foundation models that automatically encode spatial data in such a way as to associate different spatial objects in numerous and nuanced ways that have otherwise alluded manual classification schemes. Taken together, these two technologies offer considerable potential for a new generation of agent-based models that contain agents who can behave in response to spatial and social prompts in a way that is realistic and has so far proven impossible to replicate using manually-programmed behavioral rules.

This paper presents a discussion of the state of the art in both LLMs and geospatial foundation models in the context of their potential role in agent-based modelling. It discusses the transformational potential of these technologies and outlines the critical questions that need to be addressed before they can be used to create robust, reliable and trustworthy models for empirical policy applications that support decision-making.

KEYWORDS: Agent-based Modeling; Large language model; Geospatial foundation model; Urban Modeling.

Full Reference:

Malleson, N., Crooks, A.T., Heppenstall, A. and Manley, E. (2025), Enhancing Spatial Reasoning and Behavior in Urban ABMs with Large-Language Models and Geospatial Foundation Models. In Cramer-Greenbaum, S., Dennett, A., and Zhong, C (eds.), Proceedings of the 19th International Conference on Computational Urban Planning and Urban Management (CUPUM), London, UK. (pdf)