Road Surface Classification for Mauritius from OpenStreetMap and AI

A 2026 dataset from the Heidelberg Institute for Geoinformation Technology (HeiGIT) provides AI-derived road surface classifications for Mauritius. It distinguishes paved and unpaved roads, covering approximately 13.7 thousand kilometers of OpenStreetMap (OSM) data, with 29.2% paved and 4.5% unpaved. The data is augmented with deep learning predictions from Mapillary imagery and urban layers from GHSU and AFRICAPOLIS.

Use Cases

• Transportation planning based on road surface type and highway classification.
• Infrastructure analysis using attributes like surface, smoothness, width, and bridge status.
• Climate emissions assessment based on paved vs. unpaved road network composition.
• GIS applications for urban/rural classification using the urban attribute.
• Validating and augmenting OpenStreetMap data with AI-predicted surface classes.

Strengths

• Includes AI-derived surface predictions (paved/unpaved) for approximately 13.7 thousand kilometers of roads.
• Combines multiple data sources: OSM, Mapillary imagery, GHSU, and AFRICAPOLIS urban layers.
• Provides detailed OSM attributes including highway type, surface, smoothness, width, and lanes.

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.
• Approximately 66.3% of road surface information is missing in the underlying OSM data.

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT).

Collection Method

Derived from OpenStreetMap (OSM) and augmented with a hybrid deep learning approach using Mapillary imagery.

Time Range

The mean timestamp of predictions is provided (DL_mean_timestamp), but the overall temporal coverage is not explicitly stated.

Freshness

Last updated 2026-03 02 17:24:11.645432; freshness should be verified.

Geography

Mauritius.