Reproducible machine learning workflow for interpretable urban classification using multi-source geospatial data, Random Forest, XGBoost, Neural Networks, and SHAP explainability. Companion repository for the accepted DLI 2026 paper.
machine-learning deep-learning random-forest geospatial pytorch remote-sensing xgboost africa lagos explainable-ai shap urban-classification dli2026
-
Updated
Jul 24, 2026 - Jupyter Notebook