Puerto Rico Road Surface and Passability Data for 4,200 km of Arterial Roads

HeiGIT produced this dataset mapping approximately 4,200 km of arterial roads in Puerto Rico using AI analysis of PlanetScope satellite imagery from 2020 and 2024. It provides road surface types, width classifications, and passability scores for motorway, trunk, primary, and secondary road segments.

Use Cases

• Identifying infrastructure improvements by analyzing the Road Surface Change column for transitions from unpaved to paved
• Planning disaster relief logistics using the Humanitarian Passability Index (HPI) to identify high-risk blockages
• Determining vehicle size restrictions for specific routes using the Road Width Class (1-3) attribute

Strengths

• 89.2% model accuracy for surface type
• Covers 4,200 km of arterial roads
• Multi-temporal surface change detection (2020-2024)
• Standardized width classes (1-3) for logistical planning

Limitations

• Geographic restriction to Puerto Rico
• Exclusion of minor and residential road classes
• AI-derived predictions may contain errors in areas with dense vegetation or cloud cover

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

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

Time Range

2020-2024

Freshness

Last updated March 2026; contains temporal comparisons between 2020 and 2024 imagery.

Geography

Puerto Rico