South Sudan Road Surface Classification from OpenStreetMap and AI

South Sudan road network data from OpenStreetMap, enhanced with AI-derived surface classifications. The dataset covers approximately 0.1612 million kilometers of roads, distinguishing paved and unpaved surfaces using a hybrid deep learning approach based on Mapillary imagery. It was created by HeiGIT and last updated in March 2026.

Use Cases

• Transportation planning based on road surface type and length statistics.
• Infrastructure analysis using attributes like highway type, surface, and smoothness.
• Climate emissions assessment leveraging the distinction between paved and unpaved roads.
• GIS applications for routing and logistics using the geospatial road network data.
• Urban/rural classification analysis based on the included urban classification attributes.

Strengths

• Includes AI-derived surface classifications for approximately 0.1612 million kilometers of roads.
• Provides specific statistics: 0.0005 million km paved (0.3146%) and 0.0617 million km unpaved (38.2843%).
• Integrates multiple data sources: OpenStreetMap, Mapillary imagery, and urban settlement layers.
• Offers multiple classification outputs (OSM-priority and DL-priority) for flexibility.

Limitations

• Row count and column details are unknown, which may limit suitability assessment.
• Approximately 0.099 million km (61.4011%) of road surface information is missing in the base OSM data.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

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

Collection Method

Surface classification derived using a hybrid deep learning approach; methodology detailed in linked papers.

Time Range

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

Freshness

Last updated 2026-03 02 17:26:39.367976.

Geography

South Sudan.