Bhutan Road Surface Classification from OpenStreetMap and AI Predictions

Approximately 27.6 km of roads are mapped in OpenStreetMap for Bhutan. The dataset, created by HeiGIT, classifies road surfaces as paved or unpaved using a hybrid deep learning approach on Mapillary imagery and was last updated in March 2026. It includes AI-derived predictions and OSM attributes, with deep learning estimates covering about 11.2% of the mapped road network.

Use Cases

• Transportation planning based on paved and unpaved road classifications.
• Infrastructure analysis based on OSM attributes like highway type, surface, and width.
• Climate emissions assessment based on road surface type and urban/rural classification.
• GIS applications for routing and logistics based on the geospatial road network data.

Strengths

• Includes AI-derived surface predictions for approximately 3.1 km of roads.
• Combines OSM data with deep learning predictions and urban classification layers.
• Available in geospatial formats (GEOJSON, GEOPACKAGE) suitable for GIS analysis.

Limitations

• Surface information is missing for approximately 24.5 km (88.8%) of roads in the base 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.

Time Range

Mean timestamp of predictions is provided via the DL_mean_timestamp attribute.

Freshness

Last updated 2026-03-02 17:17:06.814483; freshness should be verified.

Geography

Bhutan.