Scaling over Space: Advancing the Model and Data Foundations of GeoAI Advances in deep learning and foundation models are raising expectations for general-purpose learning and creating new opportunities to harness the geospatial data revolution for Earth monitoring and scientific discovery, with broad benefits for agriculture, energy, water, transportation, smart cities, and disaster response. At the same time, major challenges remain for large-scale geospatial applications, including spatial variability that substantially weakens model generalization, limited and localized training data, and high computational demands that constrain and slow scientific discovery. This talk will discuss both AI model and data foundations for scaling geospatial applications, including geo-aware learning, knowledge-guided learning, task-aligned pretraining, and new benchmark datasets.
Sergii Skakun, Univ. of Maryland: ON THE INFERENCE FROM SATELLITE-BASED CLASSIFICATION MAPS FOR AREA ESTIMATION Luyu Liu, Texas A&M Univ.: Disentangling and Tackling the Spatiotemporal Biases in Social Sensing Data: A Cognitive-behavioral Approach Jielu Zhang, Harvard Univ.: SpatialCausal: a spatially-aware causal inference deep learning model for out-of-hospital cardiac arrest survival prediction Mehak Sachdeva, Florida State Univ.: Simulating the Precursor: Generative AI and Counterfactual Scenario Modeling of Partisan Mobility and Spatial Segregation
Wednesday June 17, 2026 10:30am - 12:00pm EDT Room A
This panel session aims to engage both panelists and the audience in a critical dialogue about the challenges, opportunities, and paths forward regarding the relationship between humans and GIS/GeoAI. We seek to explore how to develop a human-centered vision of GIScience and GeoAI that is both socially responsible and cognitively informed.
Dr. Shih-Lung Shaw is Chancellor’s Professor and Alvin and Sally Beaman Professor in the Department of Geography and Sustainability at the University of Tennessee, Knoxville. His research interests cover GIS for transportation, space-time GIS, time geography, transportation geography... Read More →
Wednesday June 17, 2026 1:30pm - 3:00pm EDT Room B
Full Research Presentations Somayeh Dodge, UC Santa Barbara: What Mobile Location Data Can Tell Us About Nature Exposure? Isaac Rand, Federal Reserve Bank of Philadelphia: Automated Digitization of the Censuses of Housing Block Statistics, 1940-1970
Lightning Talks Xuebin Wei, James Madison Univ.: Building an AI Teaching Stack for GeoAI Education Peter Kedron, UC Santa Barbara: Spatial Reasoning and identification in Causal Inference Lei Song, Rutgers Univ.: Explainable AI Reveals How Precipitation Modulates Thermal Effects Across Vertebrates Elizabeth Newnam, Temple Univ.: Effects of NDVI Exposure on Cannabis Use Disorder Treatment
Wednesday June 17, 2026 1:30pm - 3:00pm EDT Room A
Ju He, Florida State Univ.: Estimating the Continuous Causal Effect of Spatial Distance on Outcomes Chen Zhang, Univ. of Connecticut: CASTED: Calibrated Anomaly-based Spatial-Temporal Event Detection Framework for Anomaly Detection in Resilience Curves Farnoosh Roozkhosh, Univ. of Georgia: Context-Augmented GeoAI for Public EV Charging: Predicting When and Where Charging Occurs Tongwei Xu, Univ. of Washington: The Geography of “AI Slop”: An Embedding-Based Spatial Analysis of AI-Generated Music Tang Sui, Univ. of Wisconsin–Madison: FireST-GraphNet: Wildfire Progression Prediction via a Temporal Graph Neural Network with Sequence Learning
Wednesday June 17, 2026 3:30pm - 5:00pm EDT Room A
