Australia Road Surface Classification from OpenStreetMap and AI

A 2026 dataset from HeiGIT (Heidelberg Institute for Geoinformation Technology) provides AI-derived road surface classifications for Australia. It covers approximately 1.83 million kilometers of roads from OpenStreetMap, distinguishing paved and unpaved surfaces using a hybrid deep learning approach. The data is augmented with predictions from Mapillary imagery and urban classification layers.

Use Cases

• Transportation planning based on paved versus unpaved road classifications.
• Infrastructure analysis using predicted road surface types and associated OSM attributes.
• Climate emissions assessment leveraging road surface data for vehicle emission modeling.
• GIS applications integrating urban classification attributes for spatial analysis.

Strengths

• Covers approximately 1.83 million kilometers of roads in Australia.
• Provides AI-derived estimates for 31.87% paved and 43.81% unpaved roads.
• Augments OSM data with an additional 0.0086 million km of surface information from Mapillary.

Limitations

• About 24.32% of road surface information is missing in the underlying OSM data.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file size are unknown, which may limit suitability assessment.

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

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

Time Range

null

Freshness

Last updated 2026-03-02 17:21:05.889596.

Geography

Australia