Mayotte Road Surface Classification from OpenStreetMap and Satellite Imagery

A March 2026 dataset from the Heidelberg Institute for Geoinformation Technology (HeiGIT) provides road surface classifications for Mayotte. It combines OpenStreetMap data with deep learning predictions from Mapillary imagery and satellite data to distinguish paved from unpaved roads. The dataset is intended for transportation planning, infrastructure analysis, and GIS applications.

Use Cases

• Transportation planning based on road surface type classifications (paved/unpaved).
• Infrastructure analysis leveraging combined classifications from OSM tags and deep learning predictions.
• Climate emissions assessment using road network characteristics and urban/rural classification.
• GIS applications utilizing geospatial road data with attributes like highway type, surface, and width.

Strengths

• Integrates multiple data sources: OpenStreetMap, Mapillary imagery, and PlanetScope satellite imagery.
• Provides AI-derived surface classifications (pred_class, pred_label) alongside original OSM attributes.
• Includes urban/rural classification (urban attribute) from global settlement layers.
• Available in common geospatial formats (GEOJSON, GEOPACKAGE).

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.
• The description reports 0.0 million km for all road length statistics, suggesting placeholder values.

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Derived from OpenStreetMap and augmented with deep learning predictions based on Mapillary street-level imagery, combined with GHSU and AFRICAPOLIS urban layers.

Time Range

The dataset's temporal coverage is not explicitly stated.

Freshness

Last updated 2026-03-02 17:16:15.077048; freshness should be verified.

Geography

Mayotte