UK Road Surface Classification from OpenStreetMap and AI Predictions

Approximately 1.2963 million kilometers of roads from OpenStreetMap for the United Kingdom, with AI-derived surface classifications for paved and unpaved segments. The dataset, created by HeiGIT and last updated in March 2026, combines OSM attributes with deep learning predictions from Mapillary imagery and urban classification layers.

Use Cases

• Transportation planning based on road surface type and highway classification attributes.
• Infrastructure analysis using predicted surface class and road length data.
• Climate emissions assessment leveraging the distinction between paved and unpaved roads.
• GIS applications utilizing geospatial road networks with urban/rural classification.

Strengths

• Covers approximately 1.2963 million kilometers of roads in the UK.
• Provides AI-derived estimates for 24.8% paved and 9.1% unpaved roads, addressing missing OSM data.
• Includes multiple classification schemes (OSM-priority and DL-priority) and urban/rural labels.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count and file size are unknown, which may limit suitability assessment.
• About 66% of road surface information is originally missing in the source OSM data.

Provenance

Source

OpenStreetMap (OSM), augmented with deep learning predictions from Mapillary imagery and GHSU/AFRICAPOLIS urban layers.

Collection Method

Surface classification derived using a hybrid deep learning approach, as detailed in a referenced arXiv paper.

Time Range

null

Freshness

Last updated 2026-03 02 17:06:22.473077; freshness should be verified.

Geography

United Kingdom of Great Britain and Northern Ireland.