Ethiopia Road Surface and Passability: 32,500 km of AI-Derived Metrics

HeiGIT produced this dataset mapping approximately 32,500 km of arterial roads in Ethiopia using PlanetScope satellite imagery from 2020 and 2024. It features AI-derived attributes for road surface, width, and a Humanitarian Passability Index (HPI) for motorway, trunk, primary, and secondary road classes.

Use Cases

• Logistics routing using the Humanitarian Passability Index (HPI) to assess vehicle accessibility for aid delivery
• Infrastructure monitoring by tracking transitions in the Road Surface Change (2020-2024) field to identify paving projects
• Transport capacity analysis using Road Width Class to identify single-lane vs two-lane segments for heavy truck flow

Strengths

• 89.2% accuracy for AI-derived surface models
• Covers 31,300 km of roads missing surface tags in OSM
• Multi-temporal coverage comparing 2020 and 2024 imagery

Limitations

• Restricted to arterial road classifications only
• AI-derived predictions may have localized errors despite high aggregate accuracy
• Geographic scope is limited to Ethiopia

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

AI-derived predictions from PlanetScope satellite imagery integrated with OpenStreetMap road geometries.

Time Range

2020-2024

Freshness

Last updated March 2026; imagery analysis covers the period between 2020 and 2024.

Geography

Ethiopia