Tonga Road Surface Classification from OpenStreetMap and AI

HeiGIT's dataset provides detailed road surface information for Tonga, distinguishing paved and unpaved roads. It combines OpenStreetMap data with AI-derived classifications from Mapillary imagery and includes urban classification attributes. The dataset was last updated on March 2, 2026.

Use Cases

• Transportation planning based on road surface type and length statistics.
• Infrastructure analysis using attributes like highway type, surface, and smoothness.
• Climate emissions assessment based on paved vs. unpaved road classifications.
• GIS applications leveraging geospatial road network data and urban/rural classification.

Strengths

• Includes AI-derived surface classifications (paved/unpaved) for approximately 0.0024 million km of roads.
• Combines multiple data sources: OpenStreetMap, Mapillary imagery, and global settlement layers.
• Provides specific statistics on paved roads (0.0001 million km) and missing surface information (0.0015 million km).

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.
• Row count and sample data are unavailable, which may limit suitability assessment.

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT), derived from OpenStreetMap.

Collection Method

Data is augmented using a hybrid deep learning approach on Mapillary imagery, combined with GHSU and AFRICAPOLIS urban layers.

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 17:06:20.310903; freshness should be verified.

Geography

Tonga.