← All research themes

Geospatial

Developing GeoAI methods for analyzing satellite imagery and extracting structured geographic information from large-scale remote sensing data.

GeoAISatellite ImageryLand CoverGeospatial

Projects

Geospatial Diffusion
Forecasting decades of land-cover change with a generative model.
GeoAISatellite ImageryGenerative ModelsDiffusionLand Cover
Open project →

Publications

Geospatial Diffusion for Land Cover Imperviousness Change Forecasting
2025
Debvrat Varshney*, Vibhas Kumar Vats*, Bhartendu Pandey, Christa Brelsford, Philipe Dias • SIGSPATIAL
* Equal contribution
This paper presents a generative AI approach for forecasting land-use and land-cover change over time. Using a diffusion model conditioned on historical and auxiliary data, we predict future imperviousness patterns across the United States at decadal scale. Our results show that generative models can provide useful large-scale forecasts and open new directions for physically informed Earth system prediction.
GeoAISatellite ImageryGenerative ModelsDiffusionLand CoverGeospatial
PDF BibTeX DOI