dkemeh1/accra-road-surface-study

Code and data for the study: Mapping Road Surface Conditions in Accra Using Multi-Sensor Satellite Data Accra Road Surface Mapping Pipeline Overview This project provides a fully reproducible workflow for analysing transport infrastructure inequality in Greater Accra, Ghana. The workflow is divided into three integrated parts: - Part 1 — Road Surface Mapping (Python) - Part 2 — Spatial Analysis (QGIS) - Part 3 — Statistical Analysis Together, these steps helps to identify, quantify, and explain the persistence of road underdevelopment in Greater Accra, Ghana using a reproducible geospatial and machine learning framework -------------------------------------------------- PART 1 — ROAD SURFACE MAPPING (PYTHON) What This Part Does This pipeline uses Sentinel-1, Sentinel-2 and Landsat-8 imagery and OpenStreetMap (OSM) data to: 1. Extract road surface tags from OSM 2. Generate weak training labels (paved vs unpaved) 3. Segment the road network into 100 m segments 4. Extract spectral features 5. Train machine learning models using spatial cross-validation 6. Predict road surface classes 7. Detect road surface changes between years 8. Compare model performance Data Download drive.google.com Place files into: project_root/ ├── snapshots/ ├── imagery/ ├── QGIS_WITH_STATISTICAL_ANALYSIS/ How to Run (Part 1) Step 1 — Install dependencies install_requirements.bat Step 2 — Run pipeline run_pipeline.bat Output (Part 1) outputs/ -------------------------------------------------- PART 2 — QGIS_WITH_STATISTICAL_ANALYSIS Overview This section provides the full QGIS environment used to: - Visualise spatial patterns - Identify blind spots - Export datasets for statistical analysis Contents of QGIS folder: - QGIS_WITH_STATISTICAL_ANALYSIS in the link below: drive.google.com How to Use 1. Open: QGIS_WITH_STATISTICAL_ANALYSIS/Qgis.qgz 2. Fix missing layers if needed 3. En …