Taiwan Arterial Road Surface and Passability Data (2020–2024)

HeiGIT produced this dataset mapping 17,700 km of arterial roads in Taiwan using AI analysis of PlanetScope satellite imagery from 2020 and 2024. It provides surface type, width classifications, and passability indices for motorway, trunk, primary, and secondary road segments.

Use Cases

• Tracking infrastructure development by identifying 'Road Surface Change' from unpaved to paved between 2020 and 2024
• Logistics and heavy vehicle routing using 'Road Width Class' to identify segments wider than 5.5 meters
• Humanitarian access assessment using the 'Humanitarian Passability Index (HPI)' to locate high-risk bottlenecks

Strengths

• 89.2% accuracy for AI-derived surface predictions
• Multi-temporal coverage (2020 and 2024) for change detection
• Standardized width classification for logistical planning

Limitations

• Focuses exclusively on arterial roads, excluding local and residential streets
• AI predictions may be affected by environmental factors like dense canopy or shadows

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

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

Time Range

2020-2024

Freshness

Last updated March 2026; contains temporal data comparing 2020 and 2024.

Geography

Taiwan