Somalia Arterial Roads: AI-Derived Surface and Passability Data

Approximately 8,000 km of Somalia's arterial road network are mapped with AI-derived surface, width, and passability attributes by HeiGIT. The data combines 2020 and 2024 PlanetScope satellite imagery with OpenStreetMap classifications to assess infrastructure changes and logistical accessibility.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to identify high-capacity routes
• Infrastructure monitoring by tracking 'unpaved to paved' transitions in the Road Surface Change field
• Road safety analysis based on Road Width Class to identify potential bottlenecks for heavy vehicles

Strengths

• 89.2% accuracy for AI-derived surface predictions
• Fills surface tag gaps for 93% of previously unmapped OSM arterial segments
• Multi-temporal coverage (2020 and 2024) for infrastructure change detection

Limitations

• Geographic scope limited to Somalia
• Excludes minor and residential road networks
• Predictions are based on satellite imagery and may not reflect real-time ground conditions like temporary washouts

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

AI-derived predictions from PlanetScope satellite imagery combined with OpenStreetMap vector data

Time Range

2020-2024

Freshness

Last updated March 2026; contains imagery-based analysis from 2020 and 2024.

Geography

Somalia