Italy Arterial Road Surface and Passability: 132,100 km Network

HeiGIT generated this geospatial dataset covering 132,100 km of arterial roads in Italy using AI analysis of PlanetScope satellite imagery from 2020 and 2024. It provides deep-learning 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 identify high-risk routes for heavy vehicles
• Infrastructure development monitoring by analyzing the Road Surface Change (2020-2024) column to detect unpaved-to-paved transitions
• Vehicle routing optimization based on Road Width Class (1-3) to ensure segments can accommodate specific truck sizes

Strengths

• 89.2% surface model accuracy
• Covers 132,100 km of arterial road network
• Includes temporal change detection between 2020 and 2024

Limitations

• AI-derived labels have a 10.8% error rate compared to ground truth
• Geographic focus is restricted to high-capacity transportation backbones
• Some segments may contain 'Unknown' labels where imagery was obstructed

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

AI inference on PlanetScope satellite imagery combined with OpenStreetMap vector data

Time Range

2020 - 2024

Freshness

Contains imagery-derived data from 2020 and 2024; last updated in March 2026.

Geography

Italy