Bhutan Arterial Roads: AI-Derived Surface and Passability Data

Bhutan's arterial road network covering approximately 2,300 km with AI-derived surface, width, and passability attributes. Produced by the Heidelberg Institute for Geoinformation Technology (HeiGIT), the data utilizes PlanetScope satellite imagery from 2020 and 2024 to fill gaps in OpenStreetMap. It focuses on high-capacity transportation routes including motorways, trunks, and primary and secondary roads.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to assess vehicle accessibility
• Infrastructure development tracking via the Road Surface Change column
• Route optimization for heavy vehicles using Road Width Class (1-3)

Strengths

• 89.2% accuracy for surface model predictions
• Fills data gaps for 71.8% of road segments lacking OSM surface tags
• Multi-temporal coverage (2020 and 2024) for change detection

Limitations

• Geographic scope limited to arterial road classes
• AI-derived attributes are probabilistic and may differ from ground-level reality

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; imagery analysis covers the period between 2020 and 2024.

Geography

Bhutan