Sierra Leone Road Surface Classification from OSM and Deep Learning

Approximately 68,800 km of roads are mapped in OpenStreetMap for Sierra Leone, with AI-derived estimates classifying 4.7% as paved and 31.6% as unpaved. The dataset, created by the Heidelberg Institute for Geoinformation Technology (HeiGIT), combines OSM data with deep learning predictions from Mapillary imagery and urban layers. It was last updated on March 2, 2026.

Use Cases

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

Strengths

• Includes AI-derived surface classifications for approximately 68,800 km of roads.
• Combines multiple data sources: OpenStreetMap, deep learning predictions from Mapillary, and urban classification layers.
• Provides detailed OSM and urban classification attributes for each road segment.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Approximately 63.7% of road surface information is reported as missing in the original OSM data.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Data originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer.

Time Range

null

Freshness

Last updated 2026-03-02 17:18:28.988260; freshness should be verified.

Geography

Sierra Leone