Croatia Arterial Road Surface and Passability: 21,200 km AI-Derived Data

HeiGIT produced this dataset mapping 21,200 km of arterial roads in Croatia using AI analysis of PlanetScope satellite imagery from 2020 and 2024. It provides deep-learning predictions for road surface, width, and a Humanitarian Passability Index (HPI) for segments classified as motorway, trunk, primary, and secondary in OpenStreetMap.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to identify routes suitable for heavy trucks
• Infrastructure monitoring by analyzing Road Surface Change (2020-2024) to detect paving projects
• Emergency routing based on Road Width Class to determine vehicle size constraints

Strengths

• 89.2% accuracy for surface model predictions
• Temporal coverage spanning 2020 to 2024
• Standardized 6-point Humanitarian Passability Index

Limitations

• Restricted to arterial road classes only
• AI-derived predictions have a documented 10.8% error rate
• Geographic scope limited to Croatia

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning inference on PlanetScope satellite imagery combined with OpenStreetMap road geometries.

Time Range

2020-2024

Freshness

Last updated March 2026; contains imagery-derived data from 2020 and 2024.

Geography

Croatia