South Korea Arterial Road Surface and Passability for 68,800 km

HeiGIT produced this dataset covering 68,800 km of arterial roads in the Republic of Korea using PlanetScope satellite imagery from 2020 and 2024. It features AI-derived attributes for road surface, width, and a Humanitarian Passability Index (HPI) to fill significant data gaps in OpenStreetMap.

Use Cases

• Logistics routing using the Humanitarian Passability Index (HPI) to assess vehicle accessibility
• Infrastructure development tracking via the Road Surface Change indicator to identify paving projects
• Fleet management using Road Width Class to filter routes suitable for heavy trucks versus light vehicles

Strengths

• 89.2% accuracy for AI-derived surface predictions
• Fills surface data for 78.7% of OSM segments that previously lacked tags
• Multi-temporal coverage (2020 and 2024) allows for infrastructure change detection

Limitations

• Restricted to arterial road classes only
• Width data is discretized into three broad categories rather than continuous measurements
• AI-derived predictions may contain errors compared to ground-level surveys

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning models applied to PlanetScope satellite imagery and integrated with OpenStreetMap road geometries.

Time Range

2020-2024

Freshness

Uses imagery from 2020 and 2024; last updated March 2026.

Geography

Republic of Korea