Tokelau Road Surface Classifications from OpenStreetMap and AI

Tokelau's road network is classified by surface type using a hybrid deep learning approach applied to OpenStreetMap data. The dataset, created by HeiGIT and last updated in March 2026, includes AI-derived predictions for paved and unpaved roads. It integrates OSM attributes with urban classification layers and is intended to fill gaps in surface information.

Use Cases

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

Strengths

• Includes AI-derived surface predictions (paved/unpaved) from a published hybrid deep learning methodology.
• Integrates multiple data sources: OpenStreetMap, Mapillary imagery, GHSU, and AFRICAPOLIS urban layers.
• Provides combined classifications that prioritize either OSM tags or deep learning predictions for flexibility.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count and dataset size are unknown, which may limit suitability assessment.
• A significant portion (approximately 50.6%) of road surface information is reported as missing in the underlying OSM data.

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; methodology detailed in linked academic papers.

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 17:05:16.170950; freshness should be verified.

Geography

Tokelau.