Research-grade geospatial ML pipeline that turns 288-band hyperspectral imagery and LiDAR-derived ground truth into city-scale pavement intelligence for NYC road and sidewalk quality analysis.
-
Updated
Dec 15, 2025 - Jupyter Notebook
Research-grade geospatial ML pipeline that turns 288-band hyperspectral imagery and LiDAR-derived ground truth into city-scale pavement intelligence for NYC road and sidewalk quality analysis.
Scientific ML and remote-sensing research code from TerraRef plant phenotyping work.
Near-term wildfire risk forecasting platform for California using H3 geospatial indexing, NASA FIRMS, AlphaEarth embeddings, weather features, baseline ML models, and a map-ready dashboard.
Classical and quantum machine-learning framework for detecting and mapping natural hydrogen prospectivity in Kazakhstan using Sentinel-2 satellite imagery.
A competition-grade, end-to-end machine learning pipeline that predicts real-time traffic demand across geographic locations using geohash spatial indexing, cyclical temporal encoding, and a tri-model ensemble optimized with Optuna hyperparameter tuning.
Environmental foresight pipeline for Lake Titicaca: source catalog, QA gates, limnology extraction, Sentinel-2 matchup tier, and honest chl-a/eutrophication baselines for an editorial data product.
To associate your repository with the geospatial-ml topic, visit your repo's landing page and select "manage topics."