Albania Road Surface and Passability Metrics for 4,600 km of Arterial Roads

HeiGIT produced this dataset of AI-derived road surface, width, and passability metrics for approximately 4,600 km of arterial roads in Albania using PlanetScope satellite imagery from 2020 and 2024. It combines OpenStreetMap (OSM) segment IDs with deep-learning predictions to provide a more complete view of national transportation infrastructure than standard crowdsourced tags.

Use Cases

• Analyzing infrastructure development by comparing DL Surface Prediction 2020 and 2024 to identify road paving trends
• Planning humanitarian logistics using the Humanitarian Passability Index (HPI) to determine accessibility for heavy vehicles
• Assessing vehicle capacity and traffic flow risks based on the Road Width Class (1-3)

Strengths

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

Limitations

• Limited to arterial roads, excluding minor or residential streets
• AI predictions may be affected by cloud cover or dense canopy in satellite imagery

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning analysis of PlanetScope satellite imagery integrated with OpenStreetMap road network data

Time Range

2020-2024

Freshness

Based on satellite imagery from 2020 and 2024; last updated March 2026.

Geography

Albania