Estonia Road Surface and Passability Data for 5,000 km of Arterial Roads

HeiGIT produced this dataset containing AI-derived road surface, width, and passability metrics for approximately 5,000 km of arterial roads in Estonia using PlanetScope satellite imagery from 2020 and 2024. It combines OpenStreetMap (OSM) segment data with deep-learning predictions to provide consistent coverage across motorway, trunk, primary, and secondary road classes.

Use Cases

• Assessing logistical constraints for heavy transport using 'Road Width Class' and 'Humanitarian Passability Index'
• Identifying infrastructure improvements by tracking 'Road Surface Change' from 2020 to 2024
• Validating and enriching OpenStreetMap 'surface' tags using AI-derived predictions

Strengths

• 89.2% accuracy for AI-derived surface predictions
• Multi-temporal coverage (2020 and 2024) for infrastructure change detection
• Standardized Humanitarian Passability Index (HPI) for logistical planning

Limitations

• Geographic scope limited to Estonia
• Excludes lower-tier road classifications like residential or service roads
• AI-derived predictions may contain errors in areas with significant cloud cover or dense tree canopy

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Deep learning analysis of PlanetScope satellite imagery integrated with OpenStreetMap vector data

Time Range

2020-2024

Freshness

Last updated March 2026; utilizes satellite imagery from 2020 and 2024.

Geography

Estonia