GIS and Agent-Based Modeling

Research Updates: AAG 2026

2026-04-02T08:44:00.005-04:00

At the AAG Annual meeting this year, two of my students gave talks about their ongoing research. Ying Zhou presented her work with a talk entitled "Exploring the Relationship between Urban Morphology and People’s Emotions." In this talk, Ying showed how one could mine social media posts to gain a sense of how different emotions are spatially spread around a city using New York city as a case study. If this sounds of interest, below you can see the abstract of the talk, the research methodology and a sample of the results.

Abstract:

Urban morphology records physical information about spatial patterns (e.g., streets and land use) and their evolution over time, as well as human settlement information. People who live in or visit a city gain experiences through interaction with its spatial patterns, and these experiences influence people’s emotions. Therefore, it is necessary to explore the spatial relationships between urban morphology and people’s emotions. Taking New York City as a case study, this research uses social media data to obtain and locate people's emotions in different parts of the city. To extract the emotion relating to specific space, we use the RoBERTa-based model to label texts in social media with six primary emotions (i.e., happiness, sadness, fear, anger, surprise, and disgust). We then used DBSCAN to identify spatial clustering features of these emotions. Finally, we compared the clustered emotions with urban morphology (both in terms of both its form and function) and how such emotions evolve and change over a span of five years. Such analysis reveals the relationship between people’s emotions and broader setting that they inhabit (i.e., the city). Moreover, these works offer bottom-up insights into how urban morphology shapes people’s feelings, which can serve as feedback for urban planning and management.

Keywords: Urban Morphology, Emotion Detection, Spatial Analysis, Urban Studies.

While in another talk, Boyu Wang continues to add new functionality to the Mesa, a python agent-based modeling toolkit, this time in the form of utilizing large language models for agent-based decision making, with a talk entitled "Mesa-LLM: Generative agent-based modeling with large language models empowered agents"

If this sounds of interest, below you can see the abstract of the talk, along with the Mesa-LLM architecture. While further details about Mesa-LLM can be found on Boyu's GitHub page: https://github.com/mesa/mesa-llm.

Abstract

Agent‐based models (ABMs) have long been used to examine how individual behaviors give rise to aggregated social and spatial phenomena. Mesa, an open source ABM library in Python, provides modular components and browser based visualization to create and analyze agent based models in the PyData ecosystem. Agents’ behaviours in these models are often governed by rule-based decisions. The recent advancements of large language models (LLMs) have created a new paradigm, namely generative agent-based modeling, where LLMs are integrated as decision-making engines so that agents can communicate, negotiate, and decide based on natural language. In this paper, we introduce Mesa-LLM, an LLM extension to the Mesa framework. Its modular design allows users to customize reasoning, memory and planning components and plug in different LLMs (e.g., GPT, Gemini, Llama). We demonstrate Mesa-LLM through Epstein’s civil violence model. In contrast to the classical model where agents act based on calculated probabilities and pre-defined thresholds, agents through Mesa-LLM have their decisions articulated in natural language. This demonstration shows how an archetypal ABM can be enriched by language-based decision making to explore complex social dynamics such as protest escalation. Through this simple example, we highlight how incorporating LLMs into ABMs opens new possibilities for geographers to model human behavior from the bottom up by leveraging generative artificial intelligence (GenAI).

Keywords: Agent-Based Modeling, Large Language Model, AI Agent, Python.

References

Wang, B., Frisch, C., Nair, S., Kazil, J. and Crooks, A.T. (2026), Mesa-LLM: Generative Agent-Based Modeling with Large Language Models Empowered Agents, The Association of American Geographers (AAG) Annual Meeting, 17th –21th March, San Francisco, CA. (pdf)
Zhou, Y. and Crooks, A.T. (2026), Exploring the Relationship between Urban Morphology and People’s Emotions, The Association of American Geographers (AAG) Annual Meeting, 17th –21th March, San Francisco, CA. (pdf)

PySGN: A Python package for constructing synthetic geospatial networks

2026-03-16T10:24:00.002-04:00

In previous posts, we have written about the generation of synthetic populations based on real world locations, and how such populations can have various types of networks associated with them. We have also written about network generation techniques in the past and keeping with this line of research, Boyu Wang, Taylor Anderson, Andreas Züfle and myself have a new paper in the Journal of Open Source Software entitled "PySGN: A Python Package for Constructing Synthetic Geospatial Networks"

In this paper we introduce a Python package that can generate geospatial networks which we have called PySGN (Python for Synthetic Geospatial Networks). For readers not familiar with geospatial networks, to quote from the online documentation we have put together:

Geospatial networks are a type of network where nodes are associated with specific geographic locations. These networks are used to model and analyze spatial relationships and interactions, such as transportation systems, communication networks, and social interactions within geographic constraints. By incorporating spatial data, geospatial networks provide insights into how location influences connectivity and network dynamics.

PySGN generates synthetic geosocial networks that mimic the spatial relationships observed in real‑world networks as it embeds nodes in geographic coordinate space, modifies connection rules to decay with distance, and allows users to incorporate clustering and preferential attachment while respecting spatial constraints. Online we provide examples of creating Geospatial Erdős-Rényi, Watts-Strogatz & Barabási-Albert Networks along with ways to sample points based on a specified bounding box or specific polygon boundaries (examples of which are shown below).

The package is intended for researchers and practitioners in fields such as urban planning, epidemiology, infrastructure resilience and social science who require robust tools for simulating and analyzing complex geospatial networks. In addition to the paper, we have also made available extensive documentation (along with examples of the various network types) at https://pysgn.readthedocs.io/en/

Examples of Geospatial Erdős-Rényi and Watts-Strogatz Networks.

Example of Geospatial Barabási-Albert Network based on different ordering strategies for how nodes are added to the network.

Examples of sampling points based on a bounding box or a specific set of polygons

Full Referece:

Wang, B., Crooks, A.T., Anderson, T., and Züfle, A. (2026), PySGN: A Python Package for Constructing Synthetic Geospatial Networks. Journal of Open Source Software, 11(119), 9346, https://doi.org/10.21105/joss.09346 (pdf)

A hybrid simulation methodology for identifying and mitigating supply chain disruptions

2026-03-02T09:12:00.000-05:00

Durring times of crisis, shocks to supply chains can propagate through the entire economy (e.g., global shortages of critical goods, such as personal protective equipment during COVID-19). At the same time, criminal organizations may disrupt and manipulate licit supply chains for financial gain or political objectives. Thus there is a strong need for modeling and simulating not only supply chain operations but also malicious actors who may act to disrupt them.

To explore this we (Abhisekh Rana, Raj Patel, Aman Goswami, Sean Luke, Alok Baveja, Carlotta Domeniconi, Benjamin Melamed, Fred Roberts, Weiwei Chen, Vladimir Menkov, Viswanath Narayan, James Jones, Hamdi Kavak and myself) have a new paper entitled "Hybrid simulation methodology for identifying and mitigating supply chain disruptions" which was recently published in the Journal of Simulation.

In the paper we introduce a novel hybrid modeling framework (implemented in MASON) designed to identify vulnerabilities across supply networks. Through the framework, we are able to analyze disruption scenarios and evaluate mitigation strategies using a pharmaceutical supply chain model (i.e., PharmaSim). As such this paper and proposed framework provides a foundation for simulation-driven planning tools that help organizations anticipate risks and strengthen supply chain resilience.

If this sounds of interest, below we provide the abstract to the paper, some of the figures which show the supply chain we model and the simulation framework along with some results. While at the bottom of the page, you can find the full referece to the paper and a link to it, while the model itself is available at https://github.com/eclab/DES-Supply-Chain-demo.

Abstract

Global disruptions have shown that shocks to supply chains can quickly ripple through entire economies, highlighting the need to identify vulnerabilities and evaluate mitigation strategies to build resilience. In this paper, we propose a simulation methodology, Hybrid Integrated Supply-Chain Simulation (HISS), to identify and mitigate potential disruptions in supply chains. We demonstrate HISS using a generic pharmaceutical supply chain model including sourcing, outsourcing, production, packaging, and distribution processes, created using MASON’s hybrid modeling capabilities. We classify disruptions from malicious actors and analyze their timing, impact, and scope. The simulation is further extended to modeling mitigation strategies and assessing their efficacy. Extensive optimization allowed us to identify worst-case disruptions and optimized safety stock strategies reduced impacts by a factor of five, while anomaly detection achieved a high recall of 0.966. The modeling approach proposed in this paper provides a basis for planning tools that support resilience and preparedness of supply chains.

Keywords: Hybrid simulation, supply chains modeling, resilience, optimization, evolutionary computation.

Visual representation of pharmaceutical supply chain (PSC), which was used to code PharmaSim

Time series of daily production flow through the active pharmaceutical ingredient (API) Production node (resilience triangles are shown in red and the number of units on the vertical axis is in millions).

Overview of the software components and their interactions.

Sample time series of numbers of packaged units with anomalies due to (left) a disruption and due to (right) normal fluctuations (the number of units on the vertical axis is in millions).

Full reference:

Rana, A., Patel, R., Goswami, A., Luke, S., Baveja, A., Domeniconi, C., Melamed, B., Roberts, F., Chen, W., Crooks, A.T., Menkov, V., Narayan, V., Jones, J. and Kavak, H. (2026). A hybrid simulation methodology for identifying and mitigating supply chain disruptions. Journal of Simulation, 1–22. https://doi.org/10.1080/17477778.2026.2628944 (pdf)

Driving Anxiety and Visual Attention in Young Drivers

2026-02-01T13:43:00.010-05:00

Over the last summer I participated in a research experience for undergraduate at the University at Buffalo (UB) hosted by the Geologic and Climate Hazards Center. In this program students spent several weeks at UB working with faculty on a diverse set of projects ranging from understanding snow events over the great lakes, forest die off to utilizing crowdsourced data to study dust events. One of the projects I was involved with resulted in a poster being presented at the 105th Transportation Research Board (TRB) Annual Meeting entitled "Driving Anxiety and Visual Attention in Young Drivers: A Driving Simulator Study".

In this study Phoebe Schrag worked alongside Austin Angulo, Irina Benedykc, Gongda Yu, Daisha Cardenas, Hayden Radel (from UB's Transportation Research and Visualization Laboratory (TRAVL)) and myself to explore driving anxiety of young drivers between the ages of 18 and 25. Using eye-tracking data from a high-fidelity virtual reality (VR) driving simulator we explored the effects of self-reported driving anxiety on visual attention, decision-making, and cognitive load. We found that driving anxiety can impair situational awareness. If this sounds of interest and you want to find out more, below you can read the abstract to the poster along with a link to the actual poster itself.

Abstract:

Motor vehicle crashes have remained the second leading cause of death among adolescents and young adults in the United States. Although high crash rates are commonly attributed to inexperience, risk-taking behavior, and underdeveloped executive functions, the role of emotional factors such as driving anxiety remain under-explored. Driving anxiety, which is characterized by persistent fear or worry while driving, may have a significant impact on young or novice drivers due to their limited experience and developing emotional regulation abilities. However, existing research has relied heavily on adult samples, self-report measures, or clinical cases, rarely incorporating real-time behavioral data from young adults. This study addresses these gaps by using eye-tracking in a high-fidelity virtual reality (VR) driving simulator to objectively evaluate the effects of self-reported driving anxiety on visual attention, decision-making, and cognitive load. Thirty-one licensed drivers aged 18–25 were classified into anxiety and non-anxiety groups using a questionnaire with reference to the Driving Cognitions Questionnaire. Participants completed five mixed urban-rural scenarios (two dynamic, two static, and one repeated dynamic) while wearing a Varjo XR3 headset with iMotions eye-tracking monitoring. Key eye-tracking metrics (e.g., dwell time proportion, fixation duration and saccade count) were analyzed using scenario-specific Welch’s t-tests (α = 0.05). The results showed that anxious drivers had significantly fewer saccadic movements in high-demand scenarios, indicating reduced scanning and increased cognitive load. These findings demonstrate how driving anxiety can impair situational awareness and suggest that targeted psychological interventions could improve attentional control. This work informs emotionally adaptive driver training for young drivers.
KEYWORDS: Driving Anxiety, Eye-Tracking, Visual Attention, Young Drivers, Cognitive Load, VR Driving Simulation.

Full Reference:

Schrag, P., Yu, G., Cardenas, D., Radel, H., Angulo, A., Crooks, A.T. and Benedyk, I. (2026), Driving Anxiety and Visual Attention in Young Drivers: A Driving Simulator Study, 105th Transportation Research Board (TRB) Annual Meeting, 11th – 15th January, Washington DC. (poster pdf)

Not just numbers: Understanding cities through their words

2026-01-05T11:48:00.001-05:00

In the past we have written how one can use social media or newspapers to study the world around us. Keeping with this theme of using text we (Xinyu Fu, Catherine Brinkley, Thomas Sanchez, Chaosu Li and myself) have a new editorial entitled "Not just numbers: Understanding cities through their words" which accompanies a special issue in Environment and Planning B entitled "Leveraging Natural Language Processing for Urban Analytics"

The editorial discusses how researchers can use natural language processing (NLP) methods to get a sense of a diverse range of issues impacting cities. To quote from the editorial, these range:

"from analyzing housing development from council planning applications (Lin et al., 2025), revealing visitor perceptions of famous attractions or passengers’ perceptions on transit service quality from social media (Luo et al., 2025; Ma et al., 2025), defining the meaning of urban imageability based on online review (Zhu et al., 2025), understanding the spatial implications of the digital economy (Occhini et al., 2025), and extracting policies from official government reports (Wang et al., 2025)."

These papers, along with the data they used, and findings are summarized in the table below, and as such demonstrate how one can move beyond purely quantitative data and methods to study cities. If this sounds of interest, please feel free to read our editorial along with the papers in the special issue.

Full reference:

Fu, X., Brinkley, C., Sanchez, T.W., Li, C. and Crooks, A.T. (2026), Not Just Numbers: Understanding Cities through their Words, Environment and Planning B, 53(1): 3-10. (pdf)

Creating and Assessing an Unconventional Global Database of Dust Storms Utilizing Generative AI

2025-12-15T10:51:00.001-05:00

In the past we have written about how one can use social media to monitor dust storms along with how multi-modal large language models (MLLMs) can be used to analyze images. At the recent American Geophysical Union (AGU) Fall Meeting we (Sage Keidel, Stuart Evans and myself) brought these two strands of research together in a poster entitled "Creating and Assessing an Unconventional Global Database of Dust Storms Utilizing Generative AI."

In this work we showcase how MLLMs are providing new opportunities and accessible methods for information extraction from imagery data using geo-located images from Flickr which have a dust keyword tag associated with it from multiple languages (e.g., Arabic, English, Spanish). We run these images through ChatGPT, which classifies them as dust storms or not and compare this classification with human classifed images. If this sounds of interest, below you can read the abstract, see the poster along with a selection of images that have been labeled as as dust storm or not and ChatGPTs confidence in its classification. While the dust storm database itself can be found here

Abstract:

Complete observations of dust events are difficult, as dust’s spatial and temporal variability means satellites may miss dust due to overpass time or cloud coverage, while ground stations may miss dust due to not being in the plume. As a result, an unknown number of dust events go unrecorded in traditional datasets. Dust’s importance both for atmospheric processes and as a health and travel hazard makes detecting dust events whenever possible important, and in particular, studies of the health impacts of dust are limited by detailed exposure information.
In recent years, social media platforms have emerged as a valuable source of unconventional data to study events such as earthquakes and flooding around the world. However, one challenge with respect to using such data is classifying and labeling it (i.e., is it a dust storm or not?). While it is relatively simple to classify textural data through natural language processing, it is not the case with imagery data. Traditionally, classifying imagery data was a complex computer vision task. However, recent advancements in generative artificial intelligence (AI) especially multi-modal large language models (MLLMs) are opening up new opportunities and offering accessible methods for information extraction from imagery data. Therefore, in this study we collected geotagged Flickr images referencing dust from around the globe from multiple languages (e.g., English, Spanish, Arabic) and use generative AI (i.e., ChatGPT) to classify the images as dust storms or not. Furthermore, we compare a sample of these classified images from ChatGPT with human classified images to assess its accuracy in classification. Our results suggest that ChatGPT can relatively accurately detect dust storms from Flickr images and thus helps us create an unconventional global database of dust storm events that might otherwise go unobserved from more traditional datasets.

Workflow

Poster

Dust storm database (click here to go to it)

Full Referece:

Keidel, S., Evans S. and Crooks, A.T. (2025), Creating and Assessing an Unconventional Global Database of Dust Storms Utilizing Generative AI, American Geophysical Union (AGU) Fall Meeting, 15th–19th December, New Orleans, LA. (pdf of poster).

Quantitative Comparison of Population Synthesis Techniques

2025-12-12T13:41:00.003-05:00

In the past we have written a number of posts on synthetic populations, however, one thing we have not done is compare the various techniques that can be used to create them. This has now changed with a new paper entitled "Quantitative Comparison of Population Synthesis Techniques" which was recently presented at the 2025 Winter Simulation Conference.

In this paper, we (David Han, Samiul Islam, Taylor Anderson, Hamdi Kavak and myself) investigate five synthetic population generation techniques (e.g., Iterative Proportional Fitting, Conditional Probabilities, Simple Random Sampling, Hill Climbing and Simulated Annealing) in parallel to synthesize population data for different North America settings (e.g., Fairfax County, VA, USA and Metro Vancouver, BC, Canada). Our findings suggest that while iterative proportional fitting and conditional probabilities techniques perform best, it also suggests at the same time that it is important to consider the basis of choosing certain methods over others for generating synthetic populations with regard to a geographic domain.

If this sounds of interest, below you can read the abstract to the paper, see some of the figures and tables that support our discussion. While at the bottom of the post you can find the full referece and a link to the paper. Moreover, in an effort to allow for reproducible science, all code and data are available to interested readers in our GitHub repository located at https://github.com/kavak-lab/synthetic-pop-comparison.

Abstract

Synthetic populations serve as the building blocks for predictive models in many domains, including transportation, epidemiology, and public policy. Therefore, using realistic synthetic populations is essential in these domains. Given the wide range of available techniques, determining which methods are most effective can be challenging. In this study, we investigate five synthetic population generation techniques in parallel to synthesize population data for various regions in North America. Our findings indicate that iterative proportional fitting (IPF) and conditional probabilities techniques perform best in different regions, geographic scales, and with increased attributes. Furthermore, IPF has lower implementation complexity, making it an ideal technique for various population synthesis tasks. We documented the evaluation process and shared our source code to enable further research on advancing the field of modeling and simulation.

A conceptual depiction of the IPF process for population synthesis.

Our four-step process used in this study.

Average R² values by geographic level and method (standard deviations in italics).

% Total absolute error (% TAE) comparison by attribute for Fairfax County.

Full Referece:

Han, D., Islam, S., Anderson, T., Crooks, A.T. and Kavak, H. (2025), Quantitative Comparison of Population Synthesis Techniques, in Azar, E., Djanatliev, A., Harper, A., Kogler, C., Ramamohan, V., Anagnostou, A. and Taylor, S.J.E. (eds.), Proceedings of the 2025 Winter Simulation Conference, Seattle, WA, IEEE. pp. 151-162. (pdf)

Integration of Community Level Data into Mathematical Models

2025-11-28T10:50:00.000-05:00

In the past we have posted about how we can utilize data and models to explore pandemics and peoples reactions to them. And while interest in the COVID might of waned, there will be future pandemics.

To this end, at the 53rd Annual Meeting of NAPCRG we (Laurene Tumiel Berhalter, Sanchit Goel, Dawn Vanderkooi, Bruce Pitman, Yinyin Ye, Jennifer Surtees and myself) had a poster entitled "Integration of Community Level Data into Mathematical Models to Predict Future Public Health Emergencies." The objective of the poster is to showcase how one can integrate 211 data into models to predict future public health emergencies. If this sounds of interest, below you can see the poster and at the bottom of the post you can access the abstract.

Full Reference:

Tumiel, L.M., Goel, S., Vanderkooi, D., Pitman E.B., Crooks A.T., Ye, Y. and Surtees, J. (2025), Integration of Community Level Data into Mathematical Models to Predict Future Public Health Emergencies, North American Primary Care Research Group (NAPCRG) 53rd Annual Meeting, 21st-25th November, Atlanta, GA (pdf).

New Paper: Modeling Wildfire Evacuation with Embedded Fuzzy Cognitive Maps

2025-11-08T18:55:00.000-05:00

While we have explored disasters in the past through agent-based models and other computational social science approaches, one area we have not explored is how one can use agent-based models to explore evacuations durring a wild fire event. This has now changed with a new paper with Zhongyu Zhou and myself entitled "Modeling Wildfire Evacuation with Embedded Fuzzy Cognitive Maps: An Agent-Based Simulation of Emotion and Social Contagion" which was recently presented at the 2025 International Conference of the Computational Social Science Society of the Americas (CSSSA).

In the paper we present an agent-based model combined with an embedded fuzzy cognitive map (FCM) to simulate residents’ evacuation behavior during a wildfire event. If this sounds of interest, below we provide the abstract to the paper along with some of the figures that showcase the model logic and some of its results. A detailed ODD, the model and the data needed to run the model can be found at: https://github.com/ozzyzhou99/LA-Wildfire-Model/. Finally, at the bottom of the post you can find the full referece to the paper and a link to it.

Abstract:

Wildfires are becoming increasingly dangerous, especially in densely populated fire-prone areas like Los Angeles. People’s evacuation decisions during wildfire events are influenced by many factors, including emotions such as fear or panic, which often affect people’s choices to evacuate. Traditional evacuation models often assume that individuals behave rationally. As a result, these models tend to overlook the influence of emotional factors on evacuation behavior. To address this issue, this study develops an agent-based model (ABM) combined with an embedded fuzzy cognitive map (FCM) to simulate residents’ evacuation behavior during a wildfire event. The model covers two types of agents: evacuees and rescuers. It focuses on how emotions change over time and how they spread among people. While we also expect to observe how these emotional changes will affect evacuation decisions. This research also considers differences between different income groups to explore whether low-income residents are more likely to panic. Results from the model show that agents with different emotions behave differently during the evacuation process. Emotional changes clearly affect how agents choose routes and whether they can respond quickly. In addition, the results suggest that income level affects emotional responses, and low-income groups are more likely to feel fear. This study highlights the value of using ABM and FCM together to better understand evacuation behavior and provides a new idea for developing fairer and more effective disaster response plans.
Keywords: Agent-Based Modeling, Emotional decision-making, GIS, Fuzzy Cognitive Map, Wildfire Evacuation.

Data used in the setting up the model experiment. (A) is household income data, (B) is location of previously affected houses, and (C) is evacuation road data.

Agent-level embedded FCM loop with social contagion.

Evacuees’ Workflow (A), Rescuers” Workflow (B).

Box plots of average emotions for three groups of experiments (50 repetitions each). From left to right, the number of people in each income group increases progres- sively. Low income (LI), middle income (MI), and high income (HI).

Full Referece

Zhou, Z. and Crooks, A.T. (2025), Modeling Wildfire Evacuation with Embedded Fuzzy Cognitive Maps:An Agent-Based Simulation of Emotion and Social Contagion, Proceedings of the 2025 International Conference of the Computational Social Science Society of the Americas, Santa Fe, NM. (pdf)

HD-GEN: A Software System for Large-Scale Human Mobility Data Generation Based on Patterns of Life

2025-11-06T17:55:00.002-05:00

Human mobility datasets are essential for investigating human behavior, mobility patterns, and traffic dynamics. In the past we have written about how one can use agent-based models to generate patterns of life trajectories datasets. Building on this work at the ACM SIGSPATIAL 2025 conference, we (Hossein Amiri, Richard Yang, Shiyang Ruan, Joon-Seok Kim, Hamdi Kavak, Andrew Crooks, Dieter Pfoser, Carola Wenk and Andreas Züfle) had a paper entitled "HD-GEN: A Software System for Large-Scale Human Mobility Data Generation Based on Patterns of Life"

In this paper, we extend our previous work by introducing a software system that provides a new suite of tools built on top of the Patterns of Life simulation framework. Specifically this work consolidates our contributions into a unified data generation pipeline that includes:

additional discussion of the motivation and applications of large-scale simulated trajectory data,
detailed instructions on running the simulation and generating datasets,
extended analysis of the shared dataset, and
an integrated GitHub repository

The proposed system enables large-scale synthetic dataset generation, either by statistically replicating real-world data or by creating datasets with user-defined properties. If this sounds of interest, below you can read the abstract to the paper, the poster that accompanies it and we have also provided detailed instructions on how to reproduce the generated datasets, and made the code and data available at https://github.com/onspatial/large-scale-dataset-generator.

Abstract

Understanding individual human mobility is critical for a wide range of applications. Real-world trajectory datasets provide valuable insights into actual movement behaviors but are often constrained by data sparsity and participant bias. Synthetic data, by contrast, offer scalability and flexibility but frequently lack realism. To address this gap, we introduce a comprehensive software pipeline for generating, calibrating, and processing large-scale human mobility datasets that integrate the realism of empirical data with the control and extensibility of Patterns-of-Life simulations. Our system consists of three integrated components. First, a genetic algorithm–based calibration module fine-tunes simulation parameters to align with real-world mobility characteristics, such as daily trip counts and radius of gyration, enabling realistic behavioral modeling. Second, a data generation engine constructs geographically grounded simulations using OpenStreetMap data to produce diverse mobility logs. Third, a data processing suite transforms raw simulation logs into structured formats suitable for downstream applications, including model training and benchmarking.
Keywords: GeoLife, Patterns of Life, Simulation, Realistic Trajectory Datasets

Dataset creation phases with HD-GEN software.

Full Reference:

Hossein, A., Yang, R., Ruan, S., Kim, J-S., Kavak, H., Crooks, A.T., Pfoser, D., Wenk, C. and Züfle, A., (2025). HDGEN: A Software System for Large-Scale Human Mobility Data Generation Based on Patterns of Life. In The 33rd ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL ’25), November 3–6, 2025, Minneapolis, MN. pp. 407-410. (pdf) (poster)

Call for Papers: Geosimulation and Its Emerging Directions with AI

2025-10-09T09:19:00.004-04:00

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:

Fuzhen Yin, University of Colorado Colorado Springs
Jeon-Young Kang, Kyung Hee University

Organizers:

Alison Heppenstall, University of Glasgow, Scotland.
Andrew Crooks, University at Buffalo, USA.
Na (Richard) Jiang, Hong Kong University of Science and Technology (Guangzhou), China
Fuzhen Yin, University of Colorado, Colorado Springs, USA.
Raja Sengupta, McGill University, Canada.
Suzana Dragicevic, Simon Fraser University, Canada.
Boyu Wang, University at Buffalo, USA.
Sarah Wise, University College London, England
Jeon-Young Kang, Kyung Hee University, South Korea
Yahya Gamal, University of Glasgow, Scotland.
Alexander Michels, University of Texas at Dallas, USA
Joon-Seok Kim, Emory University, USA

Sponsor Groups:

LLMs and ABMs

2025-08-01T11:56:00.001-04:00

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)

Examining spatial expansion and stemming strategies of urban shrinkage

2025-07-18T17:47:00.000-04:00

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)

New Editorial: Generative AI and Urban Modeling

2025-07-05T11:21:00.001-04:00

In the current issue of Environment and Planning B, we (Boyu Wang, Na 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)

CUPUM 2025

2025-06-30T16:35:00.004-04:00

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)

Talks: ABM, AI and other Thoughts

2025-06-21T15:26:00.002-04:00

This is a slightly different post to normal, in the sense its not really about papers but my take on agent-based modeling, urban analytics and the growth of Artificial Intelligence impacting both.

First up, while I was in Santa Fe last October for the 2024 International Conference of the Computational Social Science Society of the Americas I was interviewed by John Cordier from Epistemix for their Flux Podcast which resulted in this "From Micro-Behaviors to Macro-Patterns: Exploring Agent-Based Models with Andrew Crooks. Rather than me trying to sum it up I will just quote from the podcast episode

"In this episode of The Flux, host John Cordier sits down with Andrew Crooks ..... They dive into the world of agent-based modeling (ABM) - what it is, why it matters, and how it helps us simulate and better understand human behavior in complex systems. From simulating traffic jams to modeling social influence on vaccine uptake, Andrew shares how data, geography, and synthetic populations are revolutionizing our ability to forecast and inform decisions. They also explore the growing role of AI tools in democratizing modeling, the evolution of computational capabilities, and even ask: what if we had run a simulation before Brexit?"

If this sounds of interest, you can listen to the full podcast here.

Next up, I was asked to give a talk back in late May to give a seminar talk at the Department of Geography and Spatial Sciences (GSS) at the University at Delaware hosted by Yao Hu. The title of the talk was "Monitoring and Analyzing Cities through the Lens of Urban Analytics" In this talk I reflect what urban analytics means to me and how the field is changing. If this sounds of interest, below you can read the abstract to my talk and also see the recording. However, before ending this I would really like to thank Yao for hosting me, and the others from the GSS and the universty at large for making it a great visit and being an engaged audience.

Abstract:

For the first time in human history, more people are living in cities than rural areas and this trend is only expected to grow in the coming decades. This growth will place unprecedented challenges on cites with respect to sustainable development especially in light of climate change and increasing populations. One way to explore and understand cities is through the lens of urban analytics, a set of methods that allow us to monitor, analyze and model urban areas. This talk will explore how urban analytics has changed over time and showcase how our understanding of cities has benefited from it. I will showcase how new sources of data can be used to monitor and analyze cities and how in turn these can be integrated into models to explore various aspects of city life from pedestrian movement to urban growth. The talk will conclude with a discussion and demonstration of how artificial intelligence can be integrated into the urban analytics toolbox and what opportunities and challenges it poses.

Also in late May, Alison Heppenstall, and myself were interviewed by Dr. Andy Collins discussing as part of the Computational Social Science Society of the Americas (CSSSA) webinar series on Agent-based modeling and simulation (ABMS). To quote from CSSSA, the purpose of these webinars is that:

"Agent-based modeling and simulation (ABMS) has been applied far and wide to better understand our world. Each new application domain brings with it existing cultures of the domain's experts, including expectations and requirements. As such, it is foolhardy to expect agent-based modeling to be standardized across all domains. As practitioners, there is a desire to understand how these domain cultures differ, how they use agent-based modeling, and what the future of agent-based modeling is within those domains. To start to grapple with these grand questions, for the ABMS community, we are proposing to run a series of interviews with experts from different domains to try to map the world of agent-based modeling."

Readers, might not be surprised but we were asked to discuss ABM in the context of geography. So if you want to hear us discuss ABM and geography, you can see the talk below. It should also be noted the CSSSA has a whole host of other webinars on their YouTube Channel.

Finally, at the start of May, I was invited to give one of the keynotes at the Inaugural AI and Cities: An International Forum for Innovation and Collaboration hosted by University of Florida entitled "Artificial intelligence and Urban Analytics: Opportunities and Challenges." This talk is slightly different from the others as the focus was more on AI, so if you are wondering what my take on AI is (or my current research), you can read the abstract to the talk below and also find a link to the recording of it.

Abstract: Urban areas now provide homes for more people than ever before, and with more and more people living in cities achieving sustainable cities is crucial for the betterment of all. Coinciding with the growth of the world’s population is the growth of artificial intelligence (AI) is which is becoming pervasive in all aspects of our daily lives. In this talk I will discuss how AI is offering us new opportunities when it come studying cities, specifically, through the lens of urban analytics. Urban analytics can be broadly defined a set of methods to explore, understand and predict the properties of cities. Through a series of examples, I will highlight how AI especially through the use of multimodal large language models (LLMs) is offering accessible methods for geographic information extraction and modeling of cities. I will showcase how AI can improve the granularity of urban data collection while at the same time provides more advanced GIS tools to practitioners in a more accessible and user-friendly way. However, AI alone is not the panacea when it comes to archiving urban sustainability and many challenges exist and the talk with conclude with these.

If the abstract sounds interesting click here to watch the talk. Also the other keynotes talks are also available online here.

Crowdsourcing dust storms utilizing social media data

2025-05-13T14:14:00.002-04:00

In the past we have explored how social media can be used to delineate earthquakes, study human-wildlife interactions, understand urban morphology, urban smells or locating wildfires among many other things.

Keeping with the last topic (i.e., locating things), in a new paper published in GeoJournal entitled "Crowdsourcing dust storms in the United States utilizing social media data," Stuart Evans, Festus Adegbola and myself explore how we can use X (formerly Twitter) and Flickr to source observations of windblown dust.

As such the paper demonstrates how social media data can act as supplementary source for dust events monitoring and captures the seasonal trends of such events. Furthermore, the paper highlights the potential of using crowdsourced data for the often overlooked field of dust monitoring that has substantial health and economic impacts.

If this sounds of interest, below we provide the abstract to the paper along with some figures which showcase our methodology and comparison with National Weather Service dust advisories and VIIRS satellite data. At the bottom of the post, you can find the full reference to the paper along with a link to it.

Abstract:

Dust storms and other dust events are natural phenomena characterized by strong winds carrying large amounts of fine particles which have significant environmental and human impacts. However, capturing the occurrence of such phenomena is a challenge. Previous studies have limitations due to available data, especially regarding short-lived, intense dust storms and events that are not captured by observing stations and satellite instruments. In recent years, the advent of social media platforms has provided a unique opportunity to access vast amounts of crowdsourced data. This paper explores the utilization of Flickr and X (Twitter) data to study dust event occurrences within the United States and their correlation with National Weather Service (NWS) advisories. The work ascertains the reliability of using crowdsourced data as a supplementary source for dust events monitoring. Our analysis of Flickr and X indicates that the Southwest region is most susceptible to dust events, with Arizona leading in the highest number of occurrences. On the other hand, the Great Plains show a scarcity of crowdsourced data related to dust events, which can be attributed to the sparsely populated nature of the region. Furthermore, seasonal analysis reveals that dust events are prevalent during the Summer months followed by Spring. These results are consistent with previous traditional studies that did not use social media of dust occurrences in the U.S., and Flickr-identified images of dust events show substantial co-occurrence with regions of NWS dust warnings. This paper highlights the potential of using crowdsourced data for the often overlooked field of dust monitoring that has substantial health and economic impacts.

Keywords: Dust storms, Crowdsourcing, Social media, Weather.

Flowchart of our workflow

Selected posts retrieved from X showing active dust events.

Selected images retrieved from Flickr showing active dust events.

Map showing the distribution of flickr-identified dust event occurrences, X-identified dust event occurrences, National Weather Service dust advisories, including dust storm (DS) warnings and blowing dust (DU) advisories.

Seasonal cycle of dust events using social media metadata, the National Weather Service advisories, and the VIIRS satellite data.

Examples of social media identified dust events and satellite observations for the same day. Brown shaded pixels indicate locations Suomi-VIIRS observed dust particles. Any VTEC warnings issued by NWS for the location are shown after the date of each dust event, with HWW and DSW indicating High Wind Warning and Dust Storm Warning, respectively.

Full Referece:

Adegbola, F., Crooks, A.T. and Evans, S.M. (2025). Crowdsourcing dust storms in the United States utilizing social media data. GeoJournal, 90(3), pp.1-18. Available at https://doi.org/10.1007/s10708-025-11359-9 (pdf)

Mapping the Invisible

2025-04-22T09:57:00.004-04:00

Readers might of noticed that recently we have been exploring the use of street view images to explore cities or how we can utilize geosocial media to understand the form of function of cities, but one thing we have not explored is the role of smell and how it shapes peoples perceptions of urban spaces. However, in a new paper recently published in the Annals of the American Association of Geographers with Qingqing Chen, Ate Poorthuis we do just that. The paper is entitled "Mapping the Invisible: Decoding Perceived Urban Smells Through Geosocial Media in New York City" In the paper we use text mining techniques to tease out smell related information from over 56 million geolocated tweets which are then assigned to specific small categories (e.g., nature, food, waste) resulting in a new smellscape map for New York city.

If this sounds of interest, below you can read the abstract to our paper, see our workflow and resulting smellscape map. While the the analysis steps, along with the smell dictionary used, are documented in the research code compendium at https://figshare.com/s/8418d47cdc5c539b78ab. Finally at the bottom of the page, you can find the full reference and a link to the paper.

Abstract:

Smells can shape people’s perceptions of urban spaces, influencing how individuals relate themselves to the environment both physically and emotionally. Although the urban environment has long been conceived as a multisensory experience, research has mainly focused on the visual dimension, leaving smell largely understudied. This article aims to construct a flexible and efficient bottom-up framework for capturing and classifying perceived urban smells from individuals based on geosocial media data, thus, increasing our understanding of this relatively neglected sensory dimension in urban studies. We take New York City as a case study and decode perceived smells by teasing out specific smell-related indicator words through text mining techniques from a historical set of geosocial media data (i.e., Twitter/X). The data set consists of more than 56 million data points sent by more than 3.2 million users. The results demonstrate that this approach, which combines quantitative analysis with qualitative insights, can not only reveal “hidden” places with clear spatial smell patterns, but also capture elusive smells that might otherwise be overlooked. By making perceived smells measurable and visible, we can gain a more nuanced understanding of smellscapes and people’s sensory experiences within the urban environment. Overall, we hope our study opens up new possibilities for understanding urban spaces through an olfactory lens and, more broadly, multisensory urban experience research.
Key Words: geosocial media, multisensory urban experiences, network analysis, New York City, smellscape, text mining, urban smells.

A framework of deriving perceived smells.

An overview of research workflow.

An overview of the six dominant overlapping smells across New York City using the weaving mapping method. The weaving map uses the concept of strands to represent attributes. Each strand here represents one specific smell category, with the intensity of the color changing based on the density of that smell category within each neighborhood (i.e., grid cells).

Full Reference:

Chen, Q., Poorthuis A. and Crooks, A.T., (2025), Mapping the Invisible: Decoding Perceived Urban Smells through Geosocial Media in New York City, Annals of the American Association of Geographers, 115(6), 1444-1464. Available at https://doi.org/10.1080/24694452.2025.2485233. (pdf)

AAG 2025 Talks

2025-03-31T16:08:00.005-04:00

As the AAG has just wrapped up I thought I would write brief (well actually quite long) post on the talks that I was involved with at the conference. These talks would not have been possible without the many great students and colleagues who I have been collaborating with over time. Below you will find a brief summary of the talks and if any sound interesting, please reach out and we can give you more details.

First up (in order in which they were presented) was "Utilizing Streetview Images for Mapping Building Attributes with ChatGPT" with Qingqing Chen and Linda See. In this talk we discussed how multimodal Large Language Models are giving us a new way to study cities, in the sense, lowering the boundary for information extraction. Using ChatGPT and street view images from Mapillary as an example, we showed how one can extract building age, usage (e.g., commercial, mixed use, residential) and estimate building height which could all be used to inform urban climate models which require detailed information on buildings.

Abstract:

With increasing rates of urbanization, many challenges are emerging regarding sustainability such as the energy usage of buildings. Coinciding with this is the growing attention of urban climate models for energy demand estimation and climate adaptation strategies. However, the applicability of these models is constrained by the lack of detailed urban surface information. Therefore, creating comprehensive datasets that capture urban surface information at a granular scale is crucial for responding to our rapidly urbanizing world. Recent advancements in Large Language Models (LLMs) have opened new opportunities in urban studies, offering accessible methods for information extraction. In this talk we explore the feasibility of ChatGPT to extract building attributes from images. Taking New York City as a case study, we collect building images from Mapillary and process them through ChatGPT by posing specific questions to extract building attributes (e.g., height, functions, age). These attributes are then compared with authoritative data. The proposed method helps address the current dearth of fine-grained surface data on urban issues, therefore enhancing the accuracy and utility of urban climate models. Overall, this study demonstrates the practical applications of ChatGPT in geographic knowledge extraction, advancing the understanding of LLMs in geographic contexts, and more broadly to the discourse on Artificial Intelligence (AI) in urban modeling and climate science.
Keywords: Buildings, ChatGPT, Large Language Models (LLMs), Mapillary, Street View Images (SVI), GeoAI.

Example of Workflow.

Reference:

Chen, Q., See, L. and Crooks, A.T. (2025), Utilizing Streetview Images for Mapping Building Attributes with ChatGPT, The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)

This was followed by a talk by lead by Qingqing Chen entitled "Multi-sensory Experiences: The Connection Between the Smell and Vision in Understanding Urban Environments" where we explored to what extent can visual data from street view imagery be used as a proxy for capturing large-scale urban smell perceptions when compared to geosocial media. Such as what visual cues evoke specific smell perceptions.

Abstract:

Smell is a crucial transversal sense, which bridges the tangible aspects of urban environments, such as exhaust and garbage, with their intangible impacts on emotions, social interactions and well-being. Despite its crucial role in our everyday life, many urban studies primarily focus on the visual dimension, potentially introducing biases in our understanding of urban spaces. This research transcends this visual-centric bias by integrating the olfactory perceptions to investigate the nuanced relationship between smell and vision in urban environments. Specifically, we utilize advanced semantic segmentation to extract visual elements from street view imagery (i.e., Mapillay) and apply casual forest analysis to examine their causal effects on smell expectations recorded from human participants. These expectations, often tied to personal experiences and/or cultural associations, are compared with real-environment smell experiences derived from geosocial media (i.e., Twitter/X). The results show that visual cues can predict smells in straightforward urban settings, such as small parks or less densely populated areas. However, in complex urban environments, the predictive power of visual cues diminishes as diverse and overlapping scents obscure specific smells, even in visually distinct areas. These findings underscore the importance of a multisensory approach in urban studies, enhancing our understanding of the complex interplay between sensory experiences and informing urban design strategies that integrate multiple senses to create more engaging and inclusive environments. This is especially important for individuals with sensory impairments, such as anosmia or visual impairments, who rely on other senses to compensate for their perception of urban environments.
Keywords: Multi-sensory Experiences, Smell and Vision; Semantic Segmentation, Causal Effects, Geosocial Media, Street View Imagery (SVI).

Workflow

Reference:

Chen, Q. and Crooks, A.T. (2025), Multi-sensory Experiences: The Connection Between the Smell and Vision in Understanding Urban Environments, The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)

In the Geosimulation session that we organized, we had a talk entitled "Large Language Models for Conceptualizing, Designing, and Generating Agent-based Models" where Na Jiang, Boyu Wang and myself presented our work on exploring using multimodal Large Language Models (LLMs) to create age-based models. In the sense as modelers, we spend a lot of time developing and writing code and we were curious what could be done though the use of LLMs.

To give a sense of what is possible, below is an example of using ChatGPT for creating a model from a published paper.

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, Large Language Models, Geospatial Simulation

Reference:

Jiang, N., Wang, B. and Crooks, A.T. (2025), Large Language Models for Conceptualizing, Designing, and Generating Agent-based Models, The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)

Next up was Ying Zhou who presented our work entitled "Identifying Environmental Characteristics That Influence Perceived Safety in Urban Spaces." In this work we explored how using social media data can be used to study the fear and how this relates to actual crimes within New York city. Broadly speaking we find through our analysis, that fear sentiment may spread out between the neighborhoods and their surrounding areas and that neighborhoods surrounded by crime-clusters may have high sentiments of fear.

Abstract:

One goal of creating livable cities is to enhance health and safety. While previous research in spatial analysis and urban planning has focused on correlations between physical environments and crime, typically relying on police-reported crime data from sources like the Crime Open Database (CODE), safety perception is inherently subjective and cannot be fully represented by objective crime statistics alone. Also, urban planning today has gradually shifted its focus from a top-down mechanism to a bottom-up mechanism, so understanding and fostering spaces where residents feel safe is essential. This research examines factors that contribute to residents’ perceived insecurity in New York City. In addition to spatial analysis of the open crime data, the research used social media data to acquire people’s perceptions. The result indicates that the aggregations of perceived unsafe locations overlapped with aggregations of crime data's locations, such as in Manhattan’s neighborhoods, but they do not overlap with each other entirely. By adopting Latent Dirichlet Allocation (LDA), a method of topic modeling, the research filtered and summarized the posted texts and contents related to the negative descriptions of places or spaces in the city, and then it identified the related characteristics of the environments. The characteristics are investigated by the method of local Moran’s I, which indicates their spatial autocorrelation in some neighborhoods in the city of New York. This research offers “bottom’s views” about urban safety for both urban planning and decision-makers, which contributes to people-centered consideration for future development and urban resource distribution.

Keywords: Safety, Crime, Urban Space, Livable Cities, Social Media, Spatial Analysis.

Methodology

Reference:

Zhou, Y. and Crooks, A.T. (2025), Identifying Environmental Characteristics That Influence Perceived Safety in Urban Spaces, The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)

The last day of the conference was another busy day with two talks. First was entitled "PySGN: A Python Package for Constructing Synthetic Geo-social Networks" where Boyu Wang presented our work (with Taylor Anderson and Andreas Züfle) on a Python package that can be used to generate synthetic geo-social networks. As readers of this blog might know we have a an interest in social networks and using them in modeling and this package provides a toolkit for others to easily create their own geosocial networks (e.g., Geospatial Erdős-Rényi, Barabási–Albert and Watts-Strogatz models). For interested readers, the source code available at: https://github.com/wang-boyu/pysgn.

Abstract:

Synthetic population has been widely used in social simulations such as traffic modeling, pedestrian movements, and the spread of infectious diseases. In recent years, much attention was focused on generating synthetic population with social networks, that captures social connections between individuals. While synthetic populations are often geographically explicit, various algorithms have been proposed to create realistic geographic social (geo-social) networks, aiming to integrate spatial information into people’s social links. We build an open-source Python package, namely PySGN, for constructing synthetic geo-social networks that incorporates position information, exhibits small-world network properties, and can be scaled to hundreds of thousands and potentially millions of nodes. We discuss different ways of parametrizing the method, by either a global average node degree, or an expected degree for each individual node. It is demonstrated through a case study with synthetic population in Buffalo, NY. By doing so, we aim to illustrate how such synthetic geo-social networks can be created, utilized, and analyzed in downstream agent-based modeling and network analysis tasks. This work is available as an open-source Python package and integrated with the PyData ecosystem (e.g., GeoPandas, NetworkX), and can be further extended with more synthetic geo-social network algorithms in the future.

Keywords: Agent-Based Modeling, Synthetic Geo-Social Network, Python, Open-Source Software

Examples of Geosocial Networks Created in PySGN

Reference:

Wang, B., Crooks, A.T., Anderson, T. and Züfle, A. (2025), PySGN: A Python Package for Constructing Synthetic Geo-social Networks. The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)

The final talk (well for me) was presented by Fuzin Yin who presented our work with Lucie Laurian and Emmanuel Frimpong Boamah entitled "Analysis of Online Mutual Aid Network during Buffalo Blizzard 2022: Actors and Weak Ties." In this work we explored what kind of support was offered and requested over Facebook groups along with their network structures durring and shortly after the event utilizing machine learning.

Abstract:

In December 2022, Buffalo, NY encountered a once-in-a-generation blizzard that dropped over 4 feet of snow. This four-day snow event halted emergency services and left 47 dead. In the face of the devastating blizzard, Buffalonian demonstrated resilience and solidarity by establishing Facebook (FB) groups to share information and coordinate behaviors including donations, wellness checks, and snow removals. These spontaneous behaviors created an essential layer of protection when the major infrastructure was down. This research has collected data from Buffalo blizzard FB groups to analyze community-led self-help behaviors. We have used machine learning to classify FB messages into four categories (e.g., requesting help, offering help, emotional support, and other), and social network analysis to explore users’ communication patterns. Results show that out of all messages (n=9,988), 37% of them express emotional support, which is followed by messages offering help (25%). While requests for help constitute a small proportion (8%), they stimulate more replies than other categories. Network statistics suggest that the mutual aid network is low-density but with a high clustering coefficient. This implies that most group members are strangers with weak ties, but their connections are in the right place to allow efficient communication. However, users do not equally benefit where people requesting or offering help are central in online conversation while pure emotional supporters are at the periphery. We conclude that during the Buffalo blizzard 2022, online interactions translate into offline mutual assistance by establishing weak ties among disconnected users to facilitate the flow of information and resources.

Keywords: crisis informatics, mutual aid, social network analysis, machine learning, social media

Results of Mutual Aid Network during Buffalo Blizzard 2022

Reference:

Yin, F., Laurian, L., Crooks, A.T. and Boamah, E.F. (2025), Analysis of Online Mutual Aid Network during Buffalo Blizzard 2022: Actors and Weak Ties, The Association of American Geographers (AAG) Annual Meeting, 24th –28th March, Detroit, MI. (pdf)

While this is a rather longer post than normal, we hope you found it interesting and also as noted at the top of the post, if any of these talks/topics are of interest to you please feel free to reach out.

Geosimulations for Addressing Societal Challenges Talks @ AAG

2025-03-24T09:07:00.005-04:00

Last year we put out a call for abstracts for presentations for our sessions Geosimulations for Addressing Societal Challenges. The session description is as follows:

There is an urgent need for research that promotes sustainability in an era of societal challenges ranging from climate change, population growth, aging and wellbeing to that of pandemics. These need to be directly fed into policy. We, as a Geosimulation community, have the skills and knowledge to use the latest theory, models and evidence to make a positive and disruptive impact. These include agent-based modeling, microsimulation and increasingly, machine learning methods. However, there are several key questions that we need to address which we seek to cover in this session. For example, What do we need to be able to contribute to policy in a more direct and timely manner? What new or existing research approaches are needed? How can we make sure they are robust enough to be used in decision making? How can geosimulation be used to link across citizens, policy and practice and respond to these societal challenges? What are the cross-scale local trade-offs that will have to be negotiated as we re-configure and transform our urban and rural environments? How can spatial data (and analysis) be used to support the co-production of truly sustainable solutions, achieve social buy-in and social acceptance? And thereby co-produce solutions with citizens and policy makers.

The call generated enough interest to allow us to organize two sessions with respect to geosimulations. With the AAG ongoing we thought we would post the session details and talks. Both sessions will take place in on Thursday the 27th of March in Room 420B, Level 4, Huntington Place.

Geosimulations for Addressing Societal Challenges (2); Time: 8:30 AM - 9:50 AM

Chair: Andrew Crooks

Presentations:

Kejian Li, Jiaqi Ge, Nik Lomax and Gary Polhill

Title: Agent-Based Modeling of Food Trade Disruptions: Insights from the Russia-Ukraine Conflict

Bryan Collins and Kathleen Liang

Title: Agent-Based Modeling to Explore Social, Economic, And Environmental Links Within the North Carolina Poultry Industry

Dylan Munson, Simon Mak and John Miller

Title: Environmental policy in the context of complex systems: statistical theory and practice

Jeon-Young Kang, Jinwoo Park, and Huiji Jeong

Title: Agent-Based Modeling for Exploring Spatial Accessibility to Urban Green Space

Yan Liu,

Title: Urban growth simulation using cellular automata and machine learning approaches

Geosimulations for Addressing Societal Challenges (2); Time: 10:10 AM - 11:30 AM

Chair: Fuzhen Yin

Presentations:

Raja Sengupta and Saeed Harati Asl

Title: Why overthink Mobility in Agent-Based Models when optimization works?

Zhongyu Zhou

Title: Strategic Response Dynamics: Simulating Evacuation and Engagement in Airport Security Scenarios

Moongi Choi, Jiwoo Seo, and Alexander Hohl

Title: Agent-Based Travel Scheduler: Derivation of Spatiotemporal Risk Areas and Travel Behaviors During Pandemic

Na Jiang, Boyu Wang and Andrew Crooks

Title: Large language models for conceptualizing, designing, and generating agent-based models

We hope to see you there.

New Editorial: Cities and disasters: What can urban analytics do?

2025-03-10T13:27:00.002-04:00

In the past I have blogged about disasters, but mainly from a social media or agent-based modeling perspective. However, after the devastating wildfires that impacted parts of Los Angeles County earlier this year led me to wonder how resilient are cities to such events? Or more generally, what role could urban analytics play on the various stages of disaster management (i.e., preparation, response, recovery, and mitigation), or how can data, models, and methods at the disposal of researchers be leveraged to better prepare us for future disasters and be linked to policy?

If these questions sound of interest, I encourage you to go and read a short editorial that I recently published in Environment and Planning B entitled "Cities and Disasters: What can Urban Analytics Do?"

Full referece:

Crooks, A.T. (2024), Cities and Disasters: What can Urban Analytics Do?, Environment and Planning B, 52(3): 523-526. (pdf)

Call for Papers: Integrating LLMs and Geospatial Foundation Models to Enhance Spatial Reasoning in ABMs

2025-03-03T08:58:00.010-05:00

We are delighted to announce a special track on “Integrating Large-Language Models and Geospatial Foundation Models to Enhance Spatial Reasoning in ABMs” as part of the Social Simulation Conference 2025, 25th to 29th August 2025 at Delft University of Technology, the Netherlands. Full conference details can be found at the end of this email.

Abstract for the Special Track:

Recent developments in the use of large language models (LLMs) offer exciting opportunities to control agent behaviour in potentially more realistic and nuanced ways than has previously been possible. However, an LLM-backed agent can only interface with their surroundings through text prompts, which is severely limiting. The integration of large language models (LLMs) and geospatial foundation models (GFMs) presents an exciting opportunity to use AI techniques to advance agent-based modelling for spatial applications, potentially allowing for agents with more comprehensive behavioural realism, as well as an improved perception of their environment.

This special track invites papers that explore how AI techniques, such as LLMs and GFMs, can enrich spatial agent based models, raising new questions about their feasibility in modelling human behaviour, in comparison to conventional approaches. There are huge challenges around computational efficiency, sustainability, bias, model validation, and integration frameworks, and we welcome papers that consider these issues as well.

Paper submission deadlines and details: https://ssc2025.tbm.tudelft.nl/important-dates/

Paper types:

Long paper (10-12 pages, excluding references – long oral presentations, will be included in the post-proceedings)
Short paper (6-9 pages, excluding references – short oral presentations, will be included in the post-proceedings)
Extended abstract (3-4 pages, excluding references – short oral presentations, will not be included in the post-proceedings)

Track Organizers:

Nick Malleson, University of Leeds, UK
Alison Heppenstall, University of Glasgow, UK
Ed Manley, University of Leeds, UK
Andrew Crooks, University of Buffalo, US

Please feel free to get in touch with any of us in case of questions.

From print to perspective: A mixed-method analysis of the convergence and divergence of COVID-19 topics in newspapers and interviews

2025-02-06T17:24:00.004-05:00

In previous posts we have noted how one can explore urban issues through newspapers, while at the same time we have used social media to explore trends in vaccinations. In a recently published paper in PLOS Digital Health entitled "From print to perspective: A mixed-method analysis of the convergence and divergence of COVID-19 topics in newspapers and interviews" with Qingqing Chen, Adam Sullivan, Jennifer Surtees, Laurene Tumiel-Berhalter and myself, we thought we would explore how COVID-19 was reported in newspapers and how this varied from interviews.

The rationale behind this was that the COVID-19 pandemic has led to diverse experiences influenced by public health measures like lockdowns and social distancing. To explore these dynamics, we introduce a novel ’big-thick’ data approach that integrates extensive U.S. newspaper data with detailed interviews. By employing natural language processing (NLP) and geoparsing techniques, we identify key topics related to the pandemic and vaccinations both in newspapers and personal narratives from interviews, and compare the (spatial) convergences and divergences between them.

We found that both sources converge to highlight the profound impacts of the pandemic on daily life. However, newspapers provide a macro-level perspective, predominately covering policy, public health efforts and economics, while interviews reveal the nuanced impacts at the micro-level, focusing on personal experiences, emotion and concerns. An intriguing finding is the pronounced concern regarding the reliability of news information from interviews. By showcasing both convergences and divergences in identified topics, our study enhances the understanding of key issues that both disseminated to and resonate with the public, contributing to the development of more effective communication strategies for future public health crises.

If this sounds of interest, below you can read the abstract to the paper, see some of the figures which include our workflow and some of the results. At the bottom of the post you can see the full reference and a link to the actual paper. While at https://figshare.com/s/339b1c0d059c189dd6a4?file=44583661 you can find the code we used for our analysis.

Abstract:

In the face of the unprecedented COVID-19 pandemic, various government-led initiatives and individual actions (e.g., lockdowns, social distancing, and masking) have resulted in diverse pandemic experiences. This study aims to explore these varied experiences to inform more proactive responses for future public health crises. Employing a novel “big-thick” data approach, we analyze and compare key pandemic-related topics that have been disseminated to the public through newspapers with those collected from the public via interviews. Specifically, we utilized 82,533 U.S. newspaper articles from January 2020 to December 2021 and supplemented this “big” dataset with “thick” data from interviews and focus groups for topic modeling. Identified key topics were contextualized, compared and visualized at different scales to reveal areas of convergence and divergence. We found seven key topics from the “big” newspaper dataset, providing a macro-level view that covers public health, policies and economics. Conversely, three divergent topics were derived from the “thick” interview data, offering a micro-level view that focuses more on individuals’ experiences, emotions and concerns. A notable finding is the public’s concern about the reliability of news information, suggesting the need for further investigation on the impacts of mass media in shaping the public’s perception and behavior. Overall, by exploring the convergence and divergence in identified topics, our study offers new insights into the complex impacts of the pandemic and enhances our understanding of key issues both disseminated to and resonating with the public, paving the way for further health communication and policy-making.

An overview of the research workflow.

The monthly distribution of collected articles in the United States from January 2020 to December 2021.

An example of identified entities labeled with predefined entity types.

The spatial distribution of newspaper articles by different scales.

The spatial distribution of identified newspaper topics across different regions in New York State.

Ordered rank of identified topics by percentage from interviews.

Full reference:

Chen, Q., Crooks, A.T., Sullivan, A.J., Surtees, J.A. and Tumiel-Berhalter, L. (2025). From Print to Perspective: A mixed-method analysis of the convergence and divergence of COVID-19 topics in newspapers and interviews, PLOS Digital Health. Available at https://doi.org/10.1371/journal.pdig.0000736. (pdf)

New Directions in Mapping the Earth’s Surface with Citizen Science and Generative

2025-01-31T09:35:00.008-05:00

In previous posts, we have written how large language models (LLMs) like ChatGPT can be used in various urban analytical applications. We have kept exploring this potential especially with respect to citizen science applications. To this end we have just published a new paper in iScience, entitled "New Directions in Mapping the Earth’s Surface with Citizen Science and Generative AI". In the paper, lead by Linda See, we discuss how multi-modal LLMs (MLLMs) which are like LMMs but can take different forms of inputs (e.g., text, images, video) and output multi-modal information (e.g., take an image and output a description) could be leveraged to enhance citizen science land cover/land use mapping campaigns. If this sounds of interest, below you can read the abstract to the paper, see some of the figures we use to build our argument, while at the bottom of the post you can see the full reference and a link to the actual paper.

Abstract:

As more satellite imagery has become openly available, efforts in mapping the Earth’s surface have accelerated. Yet the accuracy of these maps is still limited by the lack of in-situ data needed to train machine learning algorithms. Citizen science has proven to be a valuable approach for collecting in-situ data through applications like Geo-Wiki and Picture Pile, but better approaches for optimizing volunteer time are still required. Although machine learning is being used in some citizen science projects, advances in generative Artificial Intelligence (AI) are yet to be fully exploited. This paper discusses how generative AI could be harnessed for land cover/land use mapping by enhancing citizen science approaches with multi-modal large language models (MLLMs), including improvements to the spatial awareness of AI.

Visual interpretation tasks undertaken by ChatGPT for (a) a wetland/mangrove landscape in South America (b) an agricultural area in central Europe.

Visual interpretation tasks undertaken by ChatGPT for identification of natural and non-natural ecosystems where ChatGPT misclassified the images as non-natural for locations in (a) Chad and (b) Austria. In (c), the image from Colombia was classified as unsure by validators but natural by ChatGPT.

Integrating multi-modal Large Language Models (MLLMs) in a citizen science visual interpretation workflow.

Full reference :

See, L., Chen, Q., Crooks, A., Bayas, J.C.L., Fraisl, D., Fritz, S., Georgieva, I., Hager, G., Hofer, M., and Lesiv, M., Malek, Ž., Milenković, M., Moorthy, I., Orduña-Cabrera, F., Pérez-Guzmán, K., Schepaschenko, D., Shchepashchenko, M., Steinhauser, J.and McCallum, I. (2025), New Directions in Mapping the Earth’s Surface with Citizen Science and Generative AI, iScience, doi: https://doi.org/10.1016/j.isci.2025.111919. (pdf)

AGU

2024-12-14T17:34:00.002-05:00

This past week we attended the American Geophysical Union (AGU) Fall Meeting in Washington DC. At the AGU we presented two abstracts.

The first follows on our work with respect to using synthetic populations within agent-based models. This work was with Na Jiang, Fuzhen Yin and Boyu Wang and entitled "A Framework for Populating Urban Digital Twins with Agents." Or more specially why digital twins need agents. Below you can see our abstract and a couple of figures showing our synthetic population workflow and how we integrate these into agent-based models.

Abstract:

Over the last few years, considerable efforts have been placed in creating digital twins from diverse fields ranging from engineering to urban planning and many things in-between. These digital twins have benefited from the growth and availability of computational power and data. For example, in urban planning the growth of computational resources and the explosion of spatial data sources(e.g. remote sensing) has lead to the creation and widespread adoption of detailed virtual urban environments or urban digital twins. However, we would argue that many of such works emphasize only the physical infrastructure or the built environment of the city instead of considering the key actors of urban systems: the people who live in them. In this work we aim to remedy this by introducing a framework that utilizes agent-based modeling to add humans to such urban digital twins. This framework consists of two components: 1)synthetic populations generated with census data; and 2) pipeline of using the population datasets for agent-based modeling applications within the urban digital twins domain. To demonstrate the utility of this framework, we have representative applications that showcase how digital twins can be created to study various urban phenomena (e.g., evacuation scenarios, traffic congestion and disease transmission). By doing so, we believe this framework will benefit researchers wishing to build urban digital twins and to explore complex urban issues with realistic populations.

Workflow of utilizing synthetic populations within agent-based models.

Examples of agent-based models utilizing our synthetic popuation.

In a different presentation, we return to how one can use social media to monitor the world around us, in this case dust storms. This work entitled "Mining unconventional data sources: creating a social media-based catalog of dust events in the Western US" is collaboration with Stuart Evans and Festus Adegbola. Generally speaking we explore how social media has the potential for a new unconventional source of observations of windblown dust. If this sounds of interest, below you can read the abstract to the paper and see the visual overlap between social media posts about dust events and official National Weather Service (NWS) dust storm warning coverage.

Abstract

Complete observations of dust events are difficult, as dust’s spatial and temporal variability means satellites may miss dust due to overpass time or cloud coverage, while ground stations may miss dust due to not being in the plume. As a result, an unknown number of dust events go unrecorded in traditional datasets. Dust’s importance both for atmospheric processes and as a health and travel hazard makes detecting dust events whenever possible important, and in particular, studies of the health impacts of dust are limited by detailed exposure information, i.e. where is there dust and when. In recent years, social media platforms have provided an opportunity to access vast user-generated data. This research utilizes geotagged Flickr and Twitter posts referencing dust in the western US, and compares it to traditional datasets including blowing dust reports from the National Weather Service and satellite observations from Suomi-VIIRS. Results show that this unconventional dataset broadly recreates the observed spatial and seasonal distributions of dust. Daily analysis of the locations of the social media posts creates a novel catalog of dust events in the western US that can be used for further research. While this catalog is necessarily incomplete, it nonetheless provides a complementary list of events to those detected by traditional means. Analysis of individual events in this catalog shows that social media captures many dust events that previously went undetected by traditional datasets.

References:

Crooks, A.T., Jiang, N., Yin, F. and Wang, B. (2024), A Framework for Populating Urban Digital Twins with Agents, American Geophysical Union (AGU) Fall Meeting, 9th–13th December, Washington, DC. (pdf)
Evans, S., Adegbola, F. and Crooks, A.T. (2024), Mining Unconventional Data Sources: Creating a Social Media-based Catalog of Dust Events in the Western US, American Geophysical Union (AGU) Fall Meeting, 9th–13th December, Washington, DC. (pdf)