Road Surface Classification for Türkiye from OpenStreetMap and AI

Türkiye's road network, comprising approximately 1.22 million kilometers mapped in OpenStreetMap, is classified into paved and unpaved surfaces using a hybrid deep learning model. The dataset, created by the Heidelberg Institute for Geoinformation Technology (HeiGIT), augments OSM data with predictions from Mapillary imagery and urban layers. It was last updated in March 2026.

Use Cases

• Transportation planning based on paved versus unpaved road classifications.
• Infrastructure analysis using predicted road surface types and OSM attributes like highway type and width.
• Climate emissions assessment leveraging the distinction between paved and unpaved road lengths.
• GIS applications utilizing the geospatial road network data and urban/rural classification.

Strengths

• Covers approximately 1.22 million kilometers of roads in Türkiye.
• Provides AI-derived estimates for 11.8% paved and 7.5% unpaved roads, quantifying a known data gap.
• Augments OSM with an additional 11,300 km of surface information from Mapillary imagery.
• Includes multiple classification fields (OSM, AI-prioritized, combined) for comparison.

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 80.7% of road surface information is reported as missing in the underlying 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 on street-level imagery.

Time Range

Mean timestamp of predictions (DL_mean_timestamp) is provided per feature, but overall temporal coverage is not specified.

Freshness

Last updated 2026-03-02 17:25:35.568928; freshness should be verified.

Geography

Türkiye.