spatial-machine-learning

SPARC is a physics-constrained spatial machine-learning pipeline that trains an ensemble of geographically-weighted models, validates causal relationships via directed acyclic graphs (DAGs), and simulates "what-if" intervention scenarios with built-in uncertainty quantification. It is designed to be domain-agnostic.

machine-learning geospatial causal-inference directed-acyclic-graph climate-adaptation climate-modeling physics-informed-ml urban-heat climate-resilience forcesmip spatial-machine-learning

• Updated Sep 1, 2026
• Python

Predicting neighbourhood deprivation change across Glasgow

python random-forest scikit-learn xgboost geopandas pysal urban-analytics geographically-weighted-regression msc-dissertation spatial-machine-learning

• Updated Aug 24, 2026
• Jupyter Notebook

Production-focused tutorials for Python geospatial machine learning and MLOps — spatial feature engineering, model training, drift detection, and deployment.

python data-science machine-learning deep-learning scikit-learn geospatial gis raster remote-sensing xgboost spatial-analysis satellite-imagery geopandas rasterio spatial-statistics geospatial-analysis mlops spatial-machine-learning

• Updated Aug 6, 2026
• Nunjucks

Explainable geospatial decision-support platform for Istanbul retail expansion: H3 microzones, network isochrones, Huff cannibalization, spatial CV demand forecasting, SHAP/AHP scoring, and budgeted maximum-coverage optimization.

docker h3 power-bi prometheus postgis folium operations-research decision-support geopandas geospatial-analytics site-selection synthetic-data explainable-ai location-allocation shap fastapi retail-analytics market-expansion spatial-machine-learning

• Updated Sep 4, 2026
• HTML