Japan Arterial Road Surface and Passability for 227,000 km

Offering AI-derived road surface, width, and passability metrics for 227,000 km of arterial roads in Japan, produced by the Heidelberg Institute for Geoinformation Technology (HeiGIT). It utilizes PlanetScope satellite imagery from 2020 and 2024 to supplement OpenStreetMap data for motorway, trunk, primary, and secondary road classes. The analysis identifies surface types and transitions with 89.2% accuracy, significantly exceeding standard OSM tag reliability.

Use Cases

• Analyzing infrastructure development by tracking transitions from unpaved to paved status using the 'Road Surface Change (2020-2024)' indicator.
• Planning heavy vehicle logistics based on the 'Road Width Class' (1-3) to identify routes capable of supporting two-lane heavy truck flow.
• Assessing disaster response accessibility using the 'Humanitarian Passability Index (HPI)' which ranks logistical accessibility from scores 1 to 6.

Strengths

• 89.2% surface model accuracy
• 0.227 million km coverage
• 2020 and 2024 temporal comparison

Limitations

• Excludes non-arterial roads
• Categorical width classes
• Broad paved/unpaved labels

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

AI-derived predictions from PlanetScope satellite imagery combined with OpenStreetMap road network data.

Time Range

2020-2024

Freshness

Last updated in March 2026, utilizing satellite imagery from 2020 and 2024.

Geography

Japan