Myanmar Road Surface and Passability: 29,300 km of AI-Derived Data

HeiGIT produced this dataset covering 29,300 km of arterial roads in Myanmar using 2020 and 2024 PlanetScope satellite imagery. It provides AI-derived classifications for road surface, width, and humanitarian passability to supplement missing OpenStreetMap (OSM) attributes. The analysis focuses on motorway, trunk, primary, and secondary road classes.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to identify segments with high blockage risk
• Infrastructure monitoring via the Road Surface Change indicator to track transitions from unpaved to paved surfaces
• Heavy vehicle route optimization using Road Width Class to identify segments wider than 5.5 meters

Strengths

• 89.2% surface prediction accuracy
• Provides surface data for 21,200 km of roads missing OSM tags
• Multi-temporal comparison between 2020 and 2024 imagery

Limitations

• AI-derived predictions may contain errors compared to ground-truth verification
• Geographic bias toward high-capacity arterial road networks

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

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

Time Range

2020-2024

Freshness

Last updated March 2026; utilizes satellite imagery from 2020 and 2024.

Geography

Myanmar