Spatial AI for Micro-scale Urban Accessibility Modeling
August 19, 2026 11:00 am (Central Time)
Abstract
3rd Place Winner in I-GUIDE's 2025-26 Spatial AI Challenge!
The GeoSocial Downscaling Model (GSDM), a Spatial AI framework, reconstructs fine-scale (~500 m) accessibility patterns from coarse human mobility data. Tested in São Paulo, GSDM uses a physics-guided U-Net architecture to downscale aggregated mobility flows while enforcing macro-micro consistency via physical constraints. It integrates national mobility metrics with socioeconomic and built-environment covariates, without relying on social media or behavioral traces. Validation includes aggregate consistency, distributional fidelity, and spatial error analysis. Outputs include high-resolution accessibility surfaces, containerized workflows, pre-trained models, and a Spatial AI Model Card with documentation and ethical guidance. All workflows are executed on the I-GUIDE Platform using Jetstream2 GPUs. GSDM provides actionable insights for resilience planning, environmental justice, and equitable service provision, addressing a critical gap in micro-scale urban accessibility modeling and directly advancing I-GUIDE’s mission of reproducible, spatially informed AI for social good.
Speakers
Rafael Albuquerque
Federal University of Rio Grande do Sul (Brazil)
Rafael Albuquerque is a Ph.D. candidate in Marketing at the Federal University of Rio Grande do Sul, Brazil, and was a Visiting Fellow at Harvard University’s Center for Geographic Analysis (2025). His research combines human mobility data, spatial analytics, and marketing to examine how consumer movement and local spatial conditions shape market exposure and performance.
Jessica Miranda
Federal University of Rio Grande do Sul (Brazil)
Jessica Miranda holds a Master's degree in Business Administration (Marketing) from the Federal University of Rio Grande do Sul (UFRGS), Brazil. She is a business consultant and researcher specializing in artificial intelligence, spatial analytics, and data-driven approaches for marketing and urban systems. Her work focuses on developing innovative methods to support decision-making through AI and spatial data analysis;
Vinicius Andrade Brei
School of Management, Federal University of Rio Grande do Sul (Brazil)