Central African Republic Road Surface Classification from OSM and AI

A 2026 dataset from the Heidelberg Institute for Geoinformation Technology (HeiGIT) provides AI-derived road surface classifications for the Central African Republic. It covers approximately 123,600 kilometers of roads from OpenStreetMap, distinguishing between paved and unpaved surfaces. The data is augmented with deep learning predictions from Mapillary imagery and urban layers from GHSU and AFRICAPOLIS.

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 paved versus unpaved road networks.
• GIS applications for humanitarian access and logistics planning using geospatial road data.

Strengths

• Includes AI-derived surface predictions for approximately 123,600 km of roads.
• Provides specific statistics: 1.395% paved (1,700 km) and 69.4411% unpaved (85,800 km).
• Combines multiple data sources: OpenStreetMap, Mapillary imagery, and urban classification layers.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Approximately 29.1639% (36,000 km) of road surface information is missing in the underlying OSM data.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Derived from OpenStreetMap and augmented with a hybrid deep learning approach using Mapillary imagery, combined with GHSU and AFRICAPOLIS urban layers.

Time Range

The dataset uses a mean timestamp from predictions (DL_mean_timestamp), but a specific temporal coverage range is not provided.

Freshness

Last updated 2026-03-02 17:04:41.131223; freshness should be verified.

Geography

Central African Republic