South Africa Road Surface Classification from OpenStreetMap and AI

A geospatial dataset detailing road surfaces across South Africa, derived from OpenStreetMap and augmented with AI predictions from Mapillary imagery. It covers approximately 1.05 million kilometers of roads, classifying them as paved or unpaved. The dataset was created by the Heidelberg Institute for Geoinformation Technology (HeiGIT) and was last updated in March 2026.

Use Cases

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

Strengths

• Covers approximately 1.05 million kilometers of roads in South Africa.
• Provides AI-derived surface classifications for roads missing OSM tags.
• Includes multiple classification schemes (OSM-priority and DL-priority) for flexibility.

Limitations

• Approximately 44.6% of road surface information is missing in the base OSM data.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

OpenStreetMap (OSM), Mapillary street-level imagery, GHSU Global Human Settlement Urban Layer 2019, AFRICAPOLIS 2020.

Collection Method

Surface classification derived using a hybrid deep learning approach on Mapillary imagery, combined with OSM attributes.

Time Range

null

Freshness

Last updated 2026-03 02 17:27:26.838136; freshness should be verified.

Geography

South Africa