Equatorial Guinea Road Surface Classification from OSM and Deep Learning

HeiGIT provides a geospatial dataset detailing road surfaces in Equatorial Guinea, derived from OpenStreetMap and enhanced with a hybrid deep learning model. The data covers approximately 16,500 kilometers of roads, with AI-derived estimates classifying 29.8% as paved and 25.8% as unpaved. The dataset was last updated in March 2026.

Use Cases

• Transportation planning based on paved versus unpaved road classifications.
• Infrastructure analysis using road attributes like highway type, surface, and width.
• Climate emissions assessment leveraging road surface data for vehicle emission modeling.
• GIS applications utilizing the geospatial geometry and urban classification attributes.

Strengths

• Integrates multiple data sources: OpenStreetMap, Mapillary imagery, GHSU, and AFRICAPOLIS urban layers.
• Provides AI-derived surface classifications for approximately 16,500 km of roads.
• Includes detailed OSM attributes such as highway type, surface, smoothness, and lanes.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Approximately 44.4% of road surface information is reported as missing in the underlying OSM data.

Provenance

Source

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

Collection Method

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

Time Range

Mean timestamp of predictions is provided in the DL_mean_timestamp field.

Freshness

Last updated 2026-03-02 17:04:44.858938; freshness should be verified.

Geography

Equatorial Guinea.