Road Surface Classification for Finland from OpenStreetMap and AI

Approximately 0.6328 million kilometers of roads in Finland are mapped, with AI-derived estimates classifying 16.9897% as paved and 40.083% as unpaved. The dataset is produced by the Heidelberg Institute for Geoinformation Technology (HeiGIT) and was last updated in March 2026. It combines OpenStreetMap data with deep learning predictions from Mapillary imagery to fill gaps in surface information.

Use Cases

• Transportation planning based on paved and unpaved road classifications.
• Infrastructure analysis using road attributes like surface type, smoothness, and width.
• Climate emissions assessment based on road surface material data.
• GIS applications integrating urban/rural classification and road network data.

Strengths

• Covers approximately 0.6328 million kilometers of roads in Finland.
• Provides AI-derived surface classifications for roads where OpenStreetMap data is missing.
• Includes multiple classification schemes (OSM-priority and DL-priority) for flexibility.

Limitations

• Row count and column-level documentation are unknown, requiring inspection after download.
• Approximately 42.9273% of road surface information is still missing from the primary OSM source.
• The dataset's freshness should be verified as the last update timestamp is from the future (2026).

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, as detailed in referenced arXiv papers.

Time Range

The mean timestamp of predictions used is provided in the 'DL_mean_timestamp' field.

Freshness

Last updated 2026-03-02 17:18:39.276898; freshness should be verified.

Geography

Finland.