Rwanda Road Surface and Passability Data for 6,800 km of Arterial Roads

HeiGIT generated this dataset covering 6,800 km of arterial roads in Rwanda using PlanetScope satellite imagery from 2020 and 2024. It features AI-derived predictions for road surface, width, and a Humanitarian Passability Index (HPI) for segments classified as motorway, trunk, primary, and secondary.

Use Cases

• Monitoring infrastructure progress by identifying transitions in Road Surface Change between 2020 and 2024
• Optimizing humanitarian logistics using the Humanitarian Passability Index (HPI) to assess route accessibility
• Evaluating transport capacity for heavy vehicles using Road Width Class

Strengths

• 89.2% surface prediction accuracy
• Temporal coverage spanning 2020 to 2024
• Fills surface data for 1,200 km of roads missing OSM tags

Limitations

• Restricted to arterial road network
• Width is binned into three classes rather than exact meters
• AI-derived labels may have localized errors

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Deep learning analysis of PlanetScope satellite imagery integrated with OpenStreetMap attributes.

Time Range

2020-2024

Freshness

Last updated March 2026; contains temporal data for 2020 and 2024.

Geography

Rwanda