Road Surface Classification for China from OpenStreetMap and Satellite Imagery

A geospatial dataset providing detailed information on road surfaces across China, distinguishing between paved and unpaved roads. The data originates from OpenStreetMap and is augmented with AI-derived surface classifications from Mapillary imagery and PlanetScope satellite data. It was created by the Heidelberg Institute for Geoinformation Technology (HeiGIT) and was last updated in March 2026.

Use Cases

• Transportation planning based on road surface type and length statistics.
• Infrastructure analysis using attributes like highway type, surface, and width.
• Climate emissions assessment based on the proportion of paved versus unpaved roads.
• GIS applications leveraging urban classification attributes like rural/urban designation.

Strengths

• Covers approximately 6.1163 million kilometers of roads mapped in OpenStreetMap.
• Provides AI-derived estimates for 0.6539 million km of paved and 0.0775 million km of unpaved roads.
• Includes multiple classification schemes (OSM-priority and DL-priority) and urban/rural attributes.

Limitations

• A significant portion (5.385 million km or 88.0428%) of road surface information is missing in the base OSM data.
• The Mapillary-derived augmentation adds only 0.012 million km (0.2231%) to fill this gap.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

OpenStreetMap (OSM), Mapillary street-level imagery, PlanetScope satellite imagery, GHSU and AFRICAPOLIS urban layers.

Collection Method

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

Time Range

Mean timestamp of predictions (DL_mean_timestamp) is provided per feature.

Freshness

Last updated 2026-03-02 17:18:07.653161; freshness should be verified.

Geography

China