Guatemala Road Surface and Passability: 9,500 km of AI-Derived Metrics

This dataset maps approximately 9,500 km of arterial roads in Guatemala using AI-derived predictions from PlanetScope satellite imagery and OpenStreetMap data. Produced by the Heidelberg Institute for Geoinformation Technology (HeiGIT), it provides road surface, width, and passability metrics for the years 2020 and 2024. The analysis focuses on high-capacity transportation segments including motorways, trunk, primary, and secondary roads.

Use Cases

• Monitoring infrastructure development by identifying segments that transitioned from unpaved to paved via the Road Surface Change indicator
• Planning disaster response logistics using the Humanitarian Passability Index (HPI) to identify high-blockage risk areas
• Assessing heavy vehicle route viability based on the Road Width Class (Class 1-3)

Strengths

• Surface model achieves 89.2% accuracy compared to 64.7% for standard OSM tags
• Provides surface data for 2,700 km of roads that lack tags in OpenStreetMap
• Includes multi-temporal comparisons between 2020 and 2024 imagery

Limitations

• Geographic scope is limited to arterial road classes only
• Predictions are AI-derived from satellite imagery and may contain classification errors compared to ground-level surveys

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

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

Time Range

2020-2024

Freshness

Contains data points from 2020 and 2024; last updated in March 2026.

Geography

Guatemala