Denmark Road Surface and Passability: 13,400 km of AI-Derived Metrics

This dataset maps approximately 13,400 km of arterial roads in Denmark with AI-derived surface, width, and passability attributes. Produced by HeiGIT, it utilizes PlanetScope satellite imagery from 2020 and 2024 to augment OpenStreetMap data with high-resolution physical characteristics. The analysis focuses specifically on motorway, trunk, primary, and secondary road classifications.

Use Cases

• Logistics and route planning using the Humanitarian Passability Index (HPI) to identify segments suitable for heavy vehicle flow
• Infrastructure monitoring by tracking the Road Surface Change indicator to identify segments upgraded from unpaved to paved between 2020 and 2024
• Transportation safety analysis using Road Width Class to identify narrow segments (Class 1, <3.5 m) with high blockage risk

Strengths

• Surface model achieves 89.2% accuracy compared to 64.7% for standard OSM surface tags
• Provides width classifications for segments where OSM data is typically missing
• Includes a standardized Humanitarian Passability Index (HPI) for logistical modeling

Limitations

• Geographic bias toward arterial roads only
• Extremely low variance in surface types for this region, with 99.26% of roads classified as paved
• AI predictions may be affected by environmental factors like canopy cover in satellite imagery

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 imagery-derived data from 2020 and 2024.

Geography

Denmark