UQGNN: Uncertainty Quantification of Graph Neural Networks for Multivariate Spatiotemporal Prediction (ACM SIGSPATIAL 2025)
highway2vec: representing OpenStreetMap microregions with respect to their road network characteristics
Busyness Graph Neural Network (BysGNN): A framework for accurate Point-of-Interest visit forecasting using dynamic graphs that capture spatial, temporal, semantic, and taxonomic contexts. Presented at ACM SIGSPATIAL 2023, this repository includes code, baselines, and experiments.
Reproduction artefact for the SIGSPATIAL '26 paper "Knowledge Channels for LLM Agents on Remote-Sensing Tasks"
Developed an optimized solution to the point-polygon query program mentioned by the ACM SIGSPATIAL CUP 2013. Showed differences between naive solution and my solution. Achieved 100% accuracy for both 'INSIDE' and 'WITHIN n' queries.
Ray Resilience: an accountable GeoAI system for place-based disaster intelligence — resilience intelligence for every place. WebGIS/smartphone PWA + Steward Harness. OASIS @ ACM SIGSPATIAL 2026 Track A.
Project page for "Rethinking Amortized Neural Representations for High-Resolution Terrain Data" (ACM SIGSPATIAL 2026). Code release coming soon.
To associate your repository with the sigspatial topic, visit your repo's landing page and select "manage topics."