Papua New Guinea Road Surface Classification from OSM and Satellite Imagery

A geospatial dataset detailing road surface types in Papua New Guinea, distinguishing paved from unpaved roads. It contains approximately 97,400 kilometers of roads mapped in OpenStreetMap, with AI-derived estimates classifying 7,600 km as paved and 29,700 km as unpaved. The dataset was created by HeiGIT and last updated in March 2026, combining OSM data with deep learning predictions from Mapillary imagery and urban classification layers.

Use Cases

• Transportation planning based on road surface type and predicted length.
• Infrastructure analysis based on attributes like highway type, surface, and smoothness.
• 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

• Includes AI-derived surface classifications for approximately 97,400 km of roads.
• Combines data from multiple sources: OpenStreetMap, Mapillary imagery, and urban settlement layers.
• Provides detailed OSM attributes including name, highway type, surface, and width.

Limitations

• Approximately 60,000 km (61.66%) of road surface information is missing in the underlying 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

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Derived from OpenStreetMap and augmented with deep learning predictions based on Mapillary street-level imagery, combined with GHSU and AFRICAPOLIS urban layers.

Time Range

The dataset uses OSM data and predictions; a specific temporal coverage is not stated.

Freshness

Last updated 2026-03-02 17:23:24.824844; freshness should be verified.

Geography

Papua New Guinea