Montenegro Road Surface Data with AI-Derived Paved and Unpaved Classifications

HeiGIT provides a geospatial dataset detailing road surfaces in Montenegro, derived from OpenStreetMap and augmented with deep learning predictions from Mapillary imagery. The dataset covers approximately 31.5 km of roads, with AI estimates classifying 19.2% as paved and 11.9% as unpaved. It was last updated on March 2, 2026.

Use Cases

• Transportation planning based on paved and unpaved road classifications.
• Infrastructure analysis using road attributes like surface type, width, and lanes.
• Climate emissions assessment leveraging road surface data for vehicle emission factors.
• GIS applications for routing and network analysis using geospatial road data.

Strengths

• Includes AI-derived surface classifications for approximately 31.5 km of roads.
• Combines OpenStreetMap data with deep learning predictions from Mapillary imagery.
• Provides multiple classification fields (e.g., pred_class, combined_surface_DL_priority) for analysis.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Approximately 68.8% of road surface information is reported as missing in the underlying OSM data.
• 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, as detailed in the referenced arXiv paper.

Time Range

Mean timestamp of predictions is available in the DL_mean_timestamp field.

Freshness

Last updated 2026-03 02 17:27:21.605388; freshness should be verified.

Geography

Montenegro.