Road Surface Classification for Macao, China, with AI-Derived Paved/Unpaved Labels

HeiGIT provides a geospatial dataset classifying road surfaces in Macao, China, as paved or unpaved. The data originates from OpenStreetMap and is augmented with deep learning predictions from Mapillary imagery, using a hybrid method detailed in an arXiv paper. The dataset was last updated on March 2, 2026.

Use Cases

• Transportation planning based on road surface type and urban/rural classification.
• Infrastructure analysis based on OSM attributes like highway type, surface, and width.
• Climate emissions assessment based on road network composition and surface material.
• GIS applications for logistics and humanitarian access planning based on spatial road data.

Strengths

• Includes AI-derived surface classifications (pred_class) from a hybrid deep learning approach.
• Combines multiple data sources: OpenStreetMap, Mapillary imagery, and global human settlement layers.
• Provides multiple classification outputs, including OSM-prioritized and DL-prioritized combined fields.

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

Heidelberg Institute for Geoinformation Technology (HeiGIT)

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 17:27:46.676879; freshness should be verified.

Geography

Macao Special Administrative Region, China