Türkiye Road Surface and Passability Data for 119,200 km of Arterial Roads

Covering 119,200 km of arterial roads in Turkey, this dataset provides AI-derived surface and width predictions generated by HeiGIT. It utilizes PlanetScope satellite imagery from 2020 and 2024 to supplement OpenStreetMap attributes with logistical accessibility metrics.

Use Cases

• Logistics routing using Road Width Class to determine if segments support two-lane heavy truck flow (Class 3)
• Infrastructure monitoring by tracking transitions in Road Surface Change (2020-2024) from unpaved to paved
• Humanitarian access assessment using the HPI score to identify segments with high blockage risk

Strengths

• 89.2% accuracy for AI-derived surface model predictions
• Covers 119,200 km of the Turkish arterial road network
• Provides temporal change detection for road paving between 2020 and 2024

Limitations

• Excludes minor, local, and residential road classes
• AI-derived attributes may contain classification errors compared to ground-truth verification
• Relies on OSM geometry which may have its own inherent spatial inaccuracies

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

AI-derived predictions from PlanetScope satellite imagery integrated with OpenStreetMap road geometries.

Time Range

2020-2024

Freshness

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

Geography

Turkey (Türkiye)