India Road Surface and Passability Data for 550,000 km of Arterial Roads

This dataset maps 0.55 million km of arterial roads in India, providing AI-derived surface types, widths, and passability scores produced by HeiGIT. Using PlanetScope satellite imagery from 2020 and 2024, the data fills surface information gaps for approximately 68.9% of the national arterial network that lacks OpenStreetMap tags.

Use Cases

• Monitoring infrastructure growth by analyzing 'Road Surface Change' from unpaved to paved
• Optimizing heavy vehicle routing using 'Road Width Class' to identify segments wider than 5.5m
• Assessing disaster response logistics using the 'Humanitarian Passability Index (HPI)'

Strengths

• 89.2% accuracy for AI-derived surface models
• Covers 0.55 million km of road infrastructure
• Fills missing surface data for 379,600 km of OSM segments

Limitations

• Geographic scope is limited to India
• Excludes minor and residential road classes
• AI-derived predictions may have errors compared to ground-truth verification

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Deep learning analysis of PlanetScope satellite imagery combined with OpenStreetMap road network data.

Time Range

2020-2024

Freshness

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

Geography

India