Pakistan Road Surface Classification from OSM and Satellite Imagery

Approximately 0.652 million kilometers of roads in Pakistan are mapped, with AI-derived estimates classifying 11.6% as paved and 9.2% as unpaved. This dataset from HeiGIT combines OpenStreetMap data with deep learning predictions from Mapillary imagery and urban layers to fill information gaps. It was last updated in March 2026 and is available in GeoJSON and GeoPackage formats.

Use Cases

• Transportation planning based on paved versus unpaved road classifications.
• Infrastructure analysis based on road attributes like surface type, width, and lanes.
• Climate emissions assessment based on road network composition and urban/rural classification.
• GIS applications for humanitarian access and logistics based on geospatial road data.

Strengths

• Covers approximately 0.652 million kilometers of roads in Pakistan.
• Provides AI-derived surface classifications for over 20% of the road network.
• Integrates multiple data sources: OSM, 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.
• About 79.2% of road surface information is missing from the original OSM source.

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology), using OpenStreetMap, Mapillary imagery, GHSU, and AFRICAPOLIS layers.

Collection Method

Surface classification derived using a hybrid deep learning approach on street-level and satellite imagery.

Time Range

null

Freshness

Last updated 2026-03-02 17:28:11.857753; freshness should be verified.

Geography

Pakistan