Canadian Road Surface Classification from OpenStreetMap and AI

Canada's road network, covering approximately 2.11 million kilometers, is classified by surface type using a hybrid deep learning approach. The dataset, created by the Heidelberg Institute for Geoinformation Technology (HeiGIT), distinguishes between paved and unpaved roads and was last updated in March 2026. It integrates OpenStreetMap data with AI predictions from Mapillary imagery and urban layers from GHSU and AFRICAPOLIS.

Use Cases

• Transportation planning based on paved versus unpaved road classifications.
• Infrastructure analysis using attributes like highway type, surface, and width.
• Climate emissions assessment leveraging road surface data for vehicle emission modeling.
• GIS applications for routing and logistics based on urban/rural classification and road quality.

Strengths

• Covers approximately 2.11 million kilometers of roads in Canada.
• Provides AI-derived estimates for 23.68% paved and 43.83% unpaved roads.
• Integrates multiple data sources: OpenStreetMap, Mapillary imagery, and urban settlement layers.

Limitations

• Approximately 0.686 million kilometers (32.48%) of road surface information is missing in the base 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

OpenStreetMap (OSM), augmented with deep learning predictions from Mapillary imagery and urban layers from GHSU and AFRICAPOLIS.

Collection Method

Surface classification derived using a hybrid deep learning approach; methodology detailed in linked arXiv papers.

Time Range

Mean timestamp of predictions is provided in the 'DL_mean_timestamp' attribute.

Freshness

Last updated 2026-03-02 17:23:31.030759; freshness should be verified.

Geography

Canada.