China Arterial Road Surface and Passability for 1.76 Million Kilometers

HeiGIT generated this geospatial dataset covering 1.76 million km of arterial roads in China using PlanetScope satellite imagery from 2020 and 2024. It provides AI-derived attributes for road surface, width, and passability for segments classified as motorway, trunk, primary, and secondary in OpenStreetMap.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to assess route accessibility
• Infrastructure monitoring by tracking Road Surface Change from 2020 to 2024
• Transport capacity modeling using Road Width Class to identify single-lane vs two-lane heavy truck routes

Strengths

• 89.2% surface prediction accuracy
• Covers 1.76 million km of road infrastructure
• Provides surface data for 1.67 million km of roads missing OSM tags

Limitations

• Limited to arterial road classes
• Width is provided as categorical classes rather than continuous measurements
• AI-derived predictions may contain errors in complex urban environments

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

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

Time Range

2020-2024

Freshness

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

Geography

China