Russia Road Surface and Passability Data for 283,700 km of Arterials

HeiGIT produced this dataset covering 0.2837 million km of arterial roads in the Russian Federation using AI analysis of PlanetScope satellite imagery from 2020 and 2024. It provides high-resolution predictions for road surface, width, and humanitarian passability for segments classified in OpenStreetMap as motorway, trunk, primary, or secondary.

Use Cases

• Monitoring infrastructure upgrades by tracking 'Road Surface Change' from unpaved to paved between 2020 and 2024
• Identifying logistical bottlenecks using 'Road Width Class' to find segments restricted to light vehicles (Class 1)
• Prioritizing humanitarian transport routes using the 'Humanitarian Passability Index (HPI)' scores

Strengths

• 89.2% surface model accuracy compared to 64.7% for standard OSM tags
• Covers 0.2837 million km of the Russian arterial road network
• Provides surface data for 74.8% of segments previously missing OSM surface tags

Limitations

• AI-derived predictions may contain classification errors compared to ground-truth verification
• Geographic scope is limited to the Russian Federation

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

AI-derived predictions from PlanetScope satellite imagery integrated with OpenStreetMap attributes

Time Range

2020-2024

Freshness

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

Geography

Russian Federation