Road Surface Classification for Kenya from OpenStreetMap and AI

Approximately 579,100 km of roads are mapped in OpenStreetMap for Kenya, with AI-derived estimates classifying 23,000 km as paved and 166,900 km as unpaved. The dataset, created by HeiGIT and last updated in March 2026, augments OSM data with deep learning predictions from Mapillary imagery and urban classification layers. It provides attributes for surface type, road characteristics, and urban/rural classification.

Use Cases

• Transportation planning based on paved vs. unpaved road classifications.
• Infrastructure analysis based on road attributes like highway type, surface, and width.
• Climate emissions assessment based on road network composition and urban/rural classification.
• GIS applications for routing and logistics based on the geospatial road network data.

Strengths

• Covers approximately 579,100 km of roads in Kenya.
• Provides AI-derived surface classifications for roads where OSM data is missing.
• Includes multiple classification schemes (OSM-priority and DL-priority) for comparison.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• About 389,200 km (67.2%) of road surface information is missing in the original OSM data.

Provenance

Source

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

Collection Method

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

Time Range

The mean timestamp of predictions used is recorded in the 'DL_mean_timestamp' field.

Freshness

Last updated 2026-03-02 17:09:04.359302; freshness should be verified.

Geography

Kenya.