Portugal Arterial Road Surface and Passability: 38,000 km AI Data

HeiGIT generated this geospatial dataset covering 38,000 km of arterial roads in Portugal using AI analysis of PlanetScope satellite imagery from 2020 and 2024. It provides high-resolution predictions for road surface, width, and passability for segments classified as motorway, trunk, primary, and secondary in OpenStreetMap.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to assess vehicle accessibility
• Infrastructure monitoring by tracking Road Surface Change from 2020 to 2024
• Emergency response routing based on Road Width Class to identify blockage risks for heavy vehicles

Strengths

• 89.2% model accuracy for surface type predictions
• Covers 38,000 km of arterial roads
• Fills surface data gaps for 38% of OSM segments in the region

Limitations

• Geographic scope limited to arterial road classes only
• Potential AI prediction errors compared to ground truth surveys
• Significant class imbalance with 95.9% of segments classified as paved

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

AI-derived predictions from PlanetScope satellite imagery combined with OpenStreetMap data

Time Range

2020-2024

Freshness

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

Geography

Portugal