UK Arterial Road Surface, Width, and Passability for 104,100 km

Offering AI-derived attributes for 104,100 km of arterial roads in the United Kingdom, developed by the Heidelberg Institute for Geoinformation Technology (HeiGIT). It combines OpenStreetMap data with deep-learning analysis of PlanetScope satellite imagery from 2020 and 2024. The records detail road surface types, width classes, and logistical passability scores for motorways, trunks, and primary/secondary roads.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to assess vehicle accessibility
• Infrastructure monitoring by tracking Road Surface Change from 2020 to 2024
• Route capacity analysis using Road Width Class to identify potential bottlenecks

Strengths

• 89.2% surface model accuracy compared to 64.7% for OSM tags
• Covers 104,100 km of the UK arterial road network
• Fills surface data for 42.9% of segments missing OSM tags
• Includes temporal change detection between 2020 and 2024

Limitations

• Restricted to arterial road classes only
• AI-derived predictions are subject to model error despite high accuracy
• Surface change detection is limited to binary unpaved-to-paved transitions

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

AI-derived predictions from PlanetScope satellite imagery combined with OpenStreetMap vector data

Time Range

2020 - 2024

Freshness

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

Geography

United Kingdom