Somalia Road Surface Data with AI-Derived Paved and Unpaved Classifications

A dataset from 2026 provides detailed road surface information for Somalia, distinguishing between paved and unpaved roads. It contains approximately 0.4947 million kilometers of roads mapped in OpenStreetMap, augmented with deep learning predictions from Mapillary imagery. The data was created by HeiGIT (Heidelberg Institute for Geoinformation Technology) and is available in GEOJSON and GEOPACKAGE formats.

Use Cases

• Transportation planning based on road surface classifications (paved/unpaved).
• Infrastructure analysis using attributes like highway type, surface, and width.
• Climate emissions assessment leveraging road length and surface type data.
• GIS applications for urban/rural classification using the urban attribute.
• Data gap analysis by comparing OSM-derived and AI-predicted surface information.

Strengths

• Contains approximately 0.4947 million kilometers of mapped roads.
• Provides AI-derived estimates for 0.0029 million km paved and 0.3665 million km unpaved roads.
• Augments OSM data with deep learning predictions from Mapillary street-level imagery.
• Includes urban/rural classification from GHSU and AFRICAPOLIS layers.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file size are unknown, which may limit suitability assessment.

Provenance

Source

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

Collection Method

Surface classification derived using a hybrid deep learning approach.

Time Range

The dataset's temporal coverage is not explicitly stated.

Freshness

Last updated 2026-03 02 17:19:11.887040; freshness should be verified.

Geography

Somalia.