Greenland Road Surface and Width Data for 100km of Arterial Roads

Approximately 100km of arterial road segments in Greenland with AI-derived surface and width attributes produced by HeiGIT. Using PlanetScope satellite imagery from 2020 and 2024, the data supplements OpenStreetMap (OSM) records for motorway, trunk, primary, and secondary roads. It provides predictions for road surface, width classes, and a logistical passability index where ground-truth data is missing.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to identify high-capacity routes
• Infrastructure development tracking via the Road Surface Change indicator
• Vehicle routing optimization based on Road Width Class to ensure heavy truck access

Strengths

• 89.2% accuracy for AI-derived surface predictions
• Provides surface data for 100% of the arterial network, filling OSM gaps
• Includes temporal change detection between 2020 and 2024

Limitations

• Very small total road length (~100km) reflecting Greenland's limited arterial infrastructure
• AI predictions may have errors in complex terrain or extreme weather conditions
• Restricted to high-capacity road classes only

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Deep learning model applied to PlanetScope satellite imagery combined with OpenStreetMap road geometries.

Time Range

2020-2024

Freshness

Last updated March 2026; compares imagery from 2020 and 2024.

Geography

Greenland