Nigeria Road Surface Classification from OpenStreetMap and AI Predictions

Nigeria's road network, covering approximately 1.0944 million kilometers mapped in OpenStreetMap, is classified into paved and unpaved surfaces using a hybrid deep learning approach. The dataset, created by the Heidelberg Institute for Geoinformation Technology (HeiGIT), augments OSM data with AI predictions from Mapillary imagery and urban layers, with the latest update in March 2026. It provides detailed attributes for each road segment, including predicted class, OSM tags, and urban classification.

Use Cases

• Transportation planning based on the classification of paved versus unpaved roads.
• Infrastructure analysis using road attributes like highway type, surface, smoothness, and width.
• Climate emissions assessment leveraging the road surface type and urban/rural classification.
• GIS applications for logistics and humanitarian access based on geospatial road network data.

Strengths

• Covers approximately 1.0944 million kilometers of roads in Nigeria.
• Provides AI-derived estimates for 0.1326 million km of paved and 0.3908 million km of unpaved roads.
• Augments OSM data with deep learning predictions to address missing surface information.
• Includes multiple classification schemes (OSM-priority and DL-priority) for flexibility.

Limitations

• Approximately 0.571 million km (52.1699%) of road surface information is missing in the underlying 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), 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 arXiv papers.

Time Range

Mean timestamp of predictions (DL_mean_timestamp) is provided per feature, but overall temporal coverage is not specified.

Freshness

Last updated 2026-03-02 17:05:12.132512; freshness should be verified.

Geography

Nigeria.