Madagascar Arterial Road Surface and Passability Data (2020-2024)

Madagascar arterial road network data featuring AI-derived surface and width attributes for approximately 7,300 km of roads. Created by HeiGIT using 2020 and 2024 PlanetScope satellite imagery, it fills gaps for 51% of roads lacking OpenStreetMap surface tags. The dataset focuses on motorway, trunk, primary, and secondary road classes.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to determine route accessibility for aid delivery
• Infrastructure development tracking via the Road Surface Change column to identify recent paving projects
• Emergency response routing based on Road Width Class to ensure segments can accommodate heavy truck passage

Strengths

• 89.2% accuracy for surface model predictions
• Fills surface data for 3,700 km of roads missing OSM tags
• Includes multi-temporal surface data for 2020 and 2024

Limitations

• Geographic scope limited to Madagascar
• Excludes non-arterial road classes
• AI-derived predictions have a documented 10.8% error rate

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; contains satellite-derived observations from 2020 and 2024.

Geography

Madagascar