Road Surface Classification for Croatia from OpenStreetMap and AI

HeiGIT provides detailed road surface data for Croatia, distinguishing paved from unpaved roads. The dataset contains approximately 168,500 kilometers of roads mapped in OpenStreetMap, with AI-derived estimates classifying 25.2% as paved and 13.7% as unpaved. It was last updated on March 2, 2026.

Use Cases

• Transportation planning based on road surface type and length data.
• Infrastructure analysis using attributes like highway type, surface, and smoothness.
• Climate emissions assessment leveraging the distinction between paved and unpaved road networks.
• GIS applications utilizing geospatial road data with urban/rural classification.

Strengths

• Contains approximately 168,500 kilometers of road data.
• Provides AI-derived surface classifications for paved and unpaved roads.
• Integrates multiple data sources: OpenStreetMap, Mapillary imagery, and urban settlement layers.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Approximately 61.1% of road surface information is reported as missing in the original OSM data.

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, with methodology detailed in linked research papers.

Time Range

Mean timestamp of predictions is provided via the DL_mean_timestamp field.

Freshness

Last updated 2026-03-02 17:02:23.530713; freshness should be verified.

Geography

Croatia