DRC Road Surface, Width, and Passability for 46,100 km of Arterial Roads

HeiGIT produced this dataset of AI-derived road surface, width, and passability metrics for 46,100 km of arterial roads in the Democratic Republic of the Congo using 2020 and 2024 PlanetScope imagery. It provides surface predictions for motorway, trunk, primary, and secondary road classes, specifically addressing the 13,300 km of the network currently lacking OpenStreetMap surface tags.

Use Cases

• Evaluating logistical accessibility for humanitarian aid using the Humanitarian Passability Index (HPI) scores
• Monitoring infrastructure development by tracking transitions in the Road Surface Change (2020-2024) column
• Determining vehicle suitability for specific routes using the Road Width Class (1-3) to identify potential blockages

Strengths

• 89.2% accuracy for AI-derived surface predictions
• Covers 46,100 km of the DRC arterial road network
• Provides surface data for 283% more road length than existing OSM tags
• Includes a standardized 6-point Humanitarian Passability Index

Limitations

• Restricted to arterial road classes only
• AI-derived attributes may have localized prediction errors
• Geographic scope is limited to the Democratic Republic of the Congo

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

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

Time Range

2020-2024

Freshness

Last updated March 2026; contains temporal comparisons between 2020 and 2024 imagery.

Geography

Democratic Republic of the Congo