Azerbaijan Road Surface and Passability Data for 10,600 km of Arterials

This dataset maps approximately 10,600 km of arterial roads in Azerbaijan, providing AI-derived surface types, widths, and passability scores generated by HeiGIT from 2020 and 2024 PlanetScope satellite imagery. It covers motorways, trunks, primary, and secondary roads, filling data gaps for the 72% of the network that lacks surface tags in OpenStreetMap.

Use Cases

• Assessing logistical accessibility for relief convoys using the 'Humanitarian Passability Index (HPI)'
• Identifying infrastructure development and road paving trends via the 'Road Surface Change' indicator
• Improving navigation routing for heavy vehicles by filtering for 'Road Width Class' 3 (>5.5 m)

Strengths

• AI surface model achieves 89.2% accuracy compared to 64.7% for standard OSM tags
• Includes multi-temporal surface predictions (2020 vs 2024) to identify infrastructure growth
• Standardized width classes (1-3) based on heavy truck flow capacity

Limitations

• Restricted to arterial road classes; does not include residential or local streets
• Predictions are derived from satellite imagery and may contain AI classification errors
• Specific license terms under 'hdx-other' may restrict commercial redistribution

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning predictions generated from PlanetScope satellite imagery integrated with OpenStreetMap road geometries.

Time Range

2020 - 2024

Freshness

Last updated March 2026; contains comparative data from 2020 and 2024.

Geography

Azerbaijan