Road Surface Classification for Réunion from OSM and Satellite Imagery

Road surface data for Réunion distinguishes paved and unpaved roads using a hybrid deep learning approach based on OpenStreetMap and Mapillary imagery. The dataset is produced by HeiGIT (Heidelberg Institute for Geoinformation Technology) and was last updated on March 2, 2026. It includes AI-derived classifications, OSM attributes, and urban classification features.

Use Cases

• Transportation planning based on road surface type and highway classification.
• Infrastructure analysis using predicted surface class and OSM attributes like width and lanes.
• Climate emissions assessment leveraging the urban/rural classification and road material data.
• GIS applications utilizing the geospatial geometry and combined surface classifications.

Strengths

• Includes AI-derived features like pred_class and combined_surface_DL_priority.
• Integrates multiple data sources: OpenStreetMap, Mapillary imagery, and global settlement layers.
• Provides urban classification attributes (urban, urban_area) for contextual analysis.
• Available in common geospatial formats: GEOJSON and GEOPACKAGE.

Limitations

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

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Derived from OpenStreetMap and augmented with deep learning predictions based on Mapillary street-level imagery.

Time Range

null

Freshness

Last updated 2026-03 02 17:05:00.419717; freshness should be verified.

Geography

Réunion