Djibouti Road Surface and Passability Data from PlanetScope (2020-2024)

HeiGIT produced this dataset of AI-derived road surface, width, and passability metrics for approximately 900 km of arterial roads in Djibouti using 2020 and 2024 PlanetScope satellite imagery. It integrates OpenStreetMap (OSM) attributes with deep-learning predictions to provide consistent coverage across motorway, trunk, primary, and secondary road classes.

Use Cases

• Monitoring infrastructure growth by identifying transitions from unpaved to paved in the 'Road Surface Change' column
• Evaluating logistical bottlenecks for heavy vehicles using 'Road Width Class' to identify segments narrower than 3.5 meters
• Prioritizing humanitarian aid routes based on the 'Humanitarian Passability Index (HPI)' scores

Strengths

• 89.2% surface model accuracy, significantly higher than the 64.7% accuracy of standard OSM surface tags
• Fills surface data gaps for 23.5% of OSM road segments that previously lacked tags
• Temporal change detection between 2020 and 2024 for infrastructure monitoring

Limitations

• Geographic scope is limited to Djibouti
• Excludes local and residential road networks
• AI-derived predictions are subject to satellite imagery resolution and environmental conditions

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Deep learning analysis of PlanetScope satellite imagery combined with OpenStreetMap vector data

Time Range

2020-2024

Freshness

Contains imagery-derived data from 2020 and 2024; last updated in March 2026.

Geography

Djibouti