Italy Road Surface Classification from OpenStreetMap and AI Predictions

A geospatial dataset detailing road surfaces across Italy, distinguishing paved and unpaved roads. It contains approximately 1.48 million kilometers of roads from OpenStreetMap, augmented with AI-derived surface predictions from Mapillary imagery. The dataset was created by the Heidelberg Institute for Geoinformation Technology (HeiGIT) and was last updated in March 2026.

Use Cases

• Transportation planning based on road surface type and highway classification.
• Infrastructure analysis using attributes like surface, smoothness, width, and bridge status.
• Climate emissions assessment based on paved versus unpaved road lengths.
• GIS applications for urban and rural classification using the urban attribute.
• Validating or augmenting OpenStreetMap data with AI-predicted surface classes.

Strengths

• Covers approximately 1.48 million kilometers of roads in Italy.
• Provides AI-derived estimates for 25.5% paved and 13.9% unpaved roads, addressing missing OSM data.
• Includes multiple classification schemes (OSM-priority, DL-priority) and urban/rural labels.
• Augments OSM data with predictions from Mapillary street-level imagery.

Limitations

• Approximately 60.7% 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 is 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, as detailed in referenced papers.

Time Range

The dataset likely reflects the timestamp of the OSM extract and Mapillary predictions used, but a specific temporal coverage range is not provided.

Freshness

Last updated 2026-03-02 17:30:49.853015; freshness should be verified.

Geography

Italy.