Type: Paper
Hybrid: No
Streamed: No
Recorded: No
Theme: Mapping the Future
Call for Papers:
We invite researchers, practitioners, and thought leaders to submit abstracts for a session at the AAG 2026 Annual Meeting. This session will explore the transformative role of GeoAnalytical techniques in fostering sustainable, healthy, resilient, and livable urban environments.
Geospatial analysis, integrating machine learning and artificial intelligence with spatial data analysis, enables unprecedented scale, accuracy, and insight into urban phenomena. Researchers are leveraging GeoAnalytical and GeoAI methods to generate actionable insights and predictive models addressing critical urban challenges, including human mobility, traffic congestion, air quality, climate resilience, health equity, and social well-being.
We welcome abstracts that showcase innovative applications, methodologies, or case studies using GeoAnalytical and GeoAI approaches to advance sustainable urban development. Join us to share your work and contribute to shaping the future of urban analytics.
Description:
GeoAnalytical techniques have long been instrumental in understanding and enhancing urban systems. The emergence of GeoAI, which integrates machine learning and artificial intelligence with spatial data analysis, has revolutionized the field by enabling unprecedented scales of accuracy and insight. This session will explore how GeoAnalytical and GeoAI methodologies are employed to generate actionable insights and predictive models addressing critical urban challenges. Topics of interest include GeoAI, sustainability, resilience, livability, and other urban issues such as human mobility, traffic congestion, air quality, health equity, and social well-being.
We welcome submissions that demonstrate innovative applications, theoretical advancements, or practical implementations of GeoAnalytical and GeoAI techniques in urban contexts. This session is also supported by the International Cartographic Association (ICA) Commission on Geospatial Analysis and Modeling.
Organizers:
Dr. Xintao LIU, Hong Kong Polytechnic University (xintao.liu@polyu.edu.hk)
Dr. Zidong YU, Hong Kong Polytechnic University (martin-zidong1.yu@polyu.edu.hk)
Chairs:
Dr. Xiao HUANG, Emory University (xiao.huang2@emory.edu)
Dr. Zidong YU, Hong Kong Polytechnic University (martin-zidong1.yu@polyu.edu.hk)
Type: Paper
Hybrid: No
Streamed: No
Recorded: No
Environmental change and extreme weather events are reshaping population movements across the globe. These events can trigger a wide range of human responses, from short-term displacement to long-term migration or resettlement. The former strains emergency response, transportation, and public health systems, while the latter permanently reshapes regional demographic and socio-economic landscapes. These processes may amplify pre-existing inequalities and threaten community resilience and long-term sustainability. Quantitative modeling of disaster-related mobility and migration remains challenging because of the complex interactions among environmental hazards, socio-economic conditions, and climate stressors.
This session builds on the growing body of research that uses spatial data science to understand human mobility and migration in the context of disasters and environmental change. It highlights how statistical modeling, geospatial artificial intelligence (GeoAI), machine learning (ML), and spatial analysis can reveal multi-scale and complex relationships between disasters and human movement. The integration of diverse data sources such as GPS trajectories, mobile phone-tracking data, social media data, remote sensing imageries, and sensor networks, can improve predictive capacity and deepen our understanding of how people respond and adapt to disasters and environmental stressors.
We welcome contributions that explore new data sources, analytical/modeling methods, and perspectives to advance the study of disaster- and climate-related mobility and migration. The session aims to foster collaboration among scientists, practitioners, community partners and policymakers, with a shared interest in enhancing equity, resilience, and sustainability in a changing environment.
Potential Topics Include (but are not limited to):
Spatial analysis, GeoAI and Machine Learning for human mobility
Spatio-temporal analysis of disaster evacuation, displacement and recovery
Disaster/climate impacts on long-term population and socio-economic changes
Migration decision modeling under compound or cascading disasters
Digital Twins for population movement simulation
Quantitative and spatial assessment of vulnerability, resilience, social equity
Geo-visualization and mapping of human dynamics
Linking human mobility patterns to health outcomes
Ethical and policy considerations
If you are interested in presenting in our session, please send your abstract and PIN to Xiang Li (xiang11@usf.edu) by the end of the abstract submission deadline (October 30, 2025). If you have any questions, please do not hesitate to email me. We look forward to receiving your submissions.
Organizers:
Xiang Li (University of South Florida)
Yi Qiang (University of South Florida)
Xiao Huang (Emory University)
Type: Paper
Hybrid: No
Streamed: No
Recorded: No
The study of human mobility is of great importance for a wide range of applications, such as transport management, urban planning, epidemic modeling, accessibility & equity assessment, among others. Current human mobility research is increasingly defined by the integration of massive spatiotemporal data and Geospatial Artificial Intelligence. This paradigm shift moves beyond descriptive pattern analysis, offering a new framework to theorize and model the fundamental mechanisms that govern urban systems, shape social structures, and influence public well-being.
This session explores this computational frontier, focusing on how Geospatial AI serves not merely as a methodological tool but as a catalyst for novel scientific discovery and theoretical advancement in human mobility research. This session welcomes research on Geospatial AI for the Science of Human Mobility, including but not limited to:
Mobility Mining and Analytics: Developing computational methods to discover patterns, flows, and anomalies in human movement, forming the empirical basis for mobility science.
AI-driven Mobility Modeling: Developing AI frameworks for high-fidelity mobility modeling. This includes novel approaches to represent, predict or generate human mobility data.
Foundation Models in Mobility Science: Exploring the next generation of AI, including the development of specialized geospatial foundation models and the novel application of Large Language Models (LLMs) to analyze, interpret, and theorize human mobility.
Urban and Societal Applications: Applying intelligent mobility analytics to critical domains such as transportation planning, public health, and urban equity.
Privacy and Ethics in Mobility Science: Investigating the challenges and frameworks for the ethical use of sensitive mobility data, including privacy-preserving techniques and societal impacts.
Algorithmic Fairness and Bias Mitigation: Critically examining how AI models perpetuate or amplify societal biases and developing techniques to ensure fairness and equity in mobility analytics.
The Reflexive Impact of AI: Critically examining the reciprocal relationship between GeoAI and society, including how AI technologies shape human mobility and transform the methods and theories of mobility science.
Abstract submission and paper presentation:
If you are interested in presenting in our session, please register and submit your abstract to the AAG annual meeting website. Once submitted, please email your presentation title, abstract (max 250 words), and your presenter identification number (PIN) by Friday, 31 October 2025, to Guangyue Li (guangyue.li@connect.polyu.hk) or Shen Liang (shen.liang@connect.polyu.hk).
Session Organizer:
Yang Xu, The Hong Kong Polytechnic University (yang.ls.xu@polyu.edu.hk)
Xiao Li, The Hong Kong Polytechnic University (xiao-shaw.li@polyu.edu.hk)
Xiao Huang, Emory University (xiao.huang2@emory.edu)
Guangyue Li, The Hong Kong Polytechnic University (guangyue.li@connect.polyu.hk)
Shen Liang, The Hong Kong Polytechnic University (shen.liang@connect.polyu.hk)
Type: Paper
Hybrid: Yes
Streamed: Yes
Recorded: No
Theme: Mapping the Future
Session Description
Human dynamics research has emerged as a transformative field within human geography, focusing on the complex interplay of human needs, aspirations, and constraints within a diverse environment. This research explores multifaceted aspects, including environmental exposure, mobility patterns, and their associated health outcomes, providing insights into why certain populations experience varying degrees of exposure to environmental and health risks. In today’s dawn of GeoAI methods, where new models are proposed, developed and deployed to measure health risks (i.e., infectious diseases), mobility issues (i.e., traffic congestion), and environmental exposure (i.e., heat stress, winter storms), this session invites contributions from scholars and researchers within the domains of geography, computer science, mathematics, transportation engineering, and urban planning to advance techniques in deep learning, reinforcement learning, graph neural networks, ensemble methods, and agent-based modeling to address these challenges.
We invite contributions that range from theoretical frameworks to practical applications, crossing transdisciplinary boundaries to advance the state-of-the-art in environmental exposure, mobility patterns, and health outcomes.
Relevant topics include, but are not limited to:
Agent-based and compartmental modeling of infectious disease transmission
Spatial interaction models including gravity models, intervening opportunities, destination choice models, and competing destination models
Graph network modeling and graph theory of mobility data representation and human mobility patterns
Deep learning for real-time air quality assessment, wildfire prediction, and heat stress exposure
Novel generative AI model frameworks such as large language models (LLM), vision-foundation models (VFM), and multimodal models for label task assignments and GIS automations in identifying and predicting spatial processes
Evaluation frameworks and validation methods for AI-based mobility models
AI-driven approaches for understanding mobility inequities and accessibility patterns
Methodological advances in analyzing real-time mobility data for geographic studies
Quantification and analysis of spatial disparities in health outcomes
AI/ML approaches to measure and model movement responses to disruptions and disasters
Health geography insights from emerging mobility data
Abstract submission and paper presentation
If you are interested in presenting in our session, please register and submit your abstract to the AAG 2026 meeting website. Once submitted, kindly email your abstract PIN either to Michaelmary Chukwu (mchukwu@umd.edu), Weishan Bai (weishanb@tamu.edu), or Guangyue Li (guangyue.li@connect.polyu.hk).
Session Organizers:
Xinyue Ye, University of Alabama, xye10@ua.edu
Xiao Huang, Emory University, xiao.huang2@emory.edu
Yang Xu, The Hong Kong Polytechnic, yang.ls.xu@polyu.edu.hk
Michaelmary Chukwu, University of Maryland, mchukwu@umd.edu
Weishan Bai, Texas A&M, weishanb@tamu.edu
Guangyue Li, The Hong Kong Polytechnic, guangyue.li@connect.polyu.hk
Type: Paper
Hybrid: Yes
Streamed: Yes
Recorded: Yes
Session Description: This session examines how spatial technologies, data-driven methods, and inclusive planning approaches can advance our understanding of urban informality within the framework of the Sustainable Development Goals (SDGs). Informal settlements are key arenas where spatial injustice, housing precarity, resource scarcity, and environmental vulnerability intersect. Mapping and analyzing these areas through geospatial intelligence, artificial intelligence, and participatory research provide new pathways toward equitable and resilient urban transformation.
Call for Participation:
We invite researchers, planners, and practitioners to contribute papers, case studies, and conceptual discussions that bridge methodological innovation and policy relevance—linking the mapping and measurement of informality to questions of governance, social equity, housing, water security, and community resilience.
Topics of interest include, but are not limited to:
GeoAI-based mapping and spatial analytics for informal settlements
Remote sensing and multi-temporal change detection
Participatory and citizen-led data initiatives
Environmental risk assessment and disaster vulnerability mapping
Water security, sanitation, and resource accessibility
Housing equity and land tenure evaluation
Policy evaluation and governance frameworks under SDG 11.1
Cross-regional and comparative studies across the Global South
This session seeks to foster interdisciplinary dialogue among scholars, planners, and policymakers to reimagine spatial justice, sustainability, and resilience in rapidly transforming urban contexts.
Session Organizer(s):
Rui Cao, The Hong Kong University of Science and Technology (Guangzhou), ruicao@hkust-gz.edu.cn
Wenyu Zhang,Texas A&M University, wenyu.zhang@tamu.edu
Yihao Wu, Harvard University,yihao_wu@gsd.harvard.edu
Weishan Bai,Texas A&M University, weishanb@tamu.edu
Yao Tong, Tsinghua University, yao_tong@tsinghua.edu.cn
Type: Paper
Hybrid: No
Streamed: No
Recorded: No
Description
Under intensifying climate change, extreme weather events, including heatwaves, floods, droughts, and storms, increasingly threaten built environments, transportation systems, and community resilience. As climate adaptation becomes imperative, leveraging artificial intelligence to predict extreme events, understand human responses, and build resilient cities represents a critical research frontier.
This session establishes a cross-disciplinary platform focusing on AI-driven extreme weather prediction, human behavioral responses, and urban resilience under climate change. We emphasize innovative applications of artificial intelligence, big data analytics, and geospatial technologies in climate adaptation research. By integrating multi-source data, including remote sensing, social media, IoT sensors, mobile trajectories, and health records, with cutting-edge methods including GeoAI, spatiotemporal machine learning, digital twins, and causal inference, researchers can predict impacts, identify vulnerabilities, and support resilience building.
We welcome scholars from geography, urban planning, transportation engineering, environmental science, public health, computational social science, and artificial intelligence. Topics include but are not limited to:
AI-driven extreme weather prediction and early warning systems
Transportation mobility and heat exposure under extreme weather
Built environment design and climate adaptation strategies
Spatiotemporal analysis of human behavioral responses to extremes
Climate vulnerability and spatial equity assessment
Social sensing and climate communication through digital platforms
Multi-scale resilience quantification and predictive modeling
Real-time monitoring and intelligent adaptive response systems
Methodological innovation and ethical considerations in AI applications
If you are interested in presenting, please send your PIN number and abstract title to Jin Rui (jin.rui@kcl.ac.uk) and Wenjing Gong (wenjinggong@tamu.edu) by December 5, 2025.
Chair(s):
Dr. Jin Rui, King’s College London
Wenjing Gong, Texas A&M University
Organizer(s):
Dr. Jin Rui, King’s College London
Wenjing Gong, Texas A&M University
Yifan Yang, Texas A&M University
Weishan Bai, Texas A&M University
Dr. Xinyue Ye, The University of Alabama