Tuvalu Road Surface Classification from OpenStreetMap and Deep Learning

A 2026 dataset from the Heidelberg Institute for Geoinformation Technology (HeiGIT) provides road surface classifications for Tuvalu. It combines OpenStreetMap data with deep learning predictions from Mapillary imagery to label roads as paved or unpaved. The dataset is intended for transportation planning, infrastructure analysis, and climate emissions assessment.

Use Cases

• Transportation planning based on paved vs. unpaved road classifications.
• Infrastructure analysis leveraging road attributes like surface, smoothness, and width.
• Climate emissions assessment using road surface data as an input for vehicle emission models.
• GIS applications for humanitarian access and logistics planning in Tuvalu.

Strengths

• Integrates multiple data sources: OpenStreetMap, Mapillary imagery, and urban classification layers.
• Provides AI-derived surface predictions (paved/unpaved) for roads where OSM data is missing.
• Includes detailed OSM attributes like highway type, surface, smoothness, and lanes.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count is unknown, which may limit suitability assessment.
• Based on AI-derived estimates, approximately 64.95% of road surface information was missing in the original OSM data.

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

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

null

Freshness

Last updated 2026-03-02 17:14:03.442504; freshness should be verified.

Geography

Tuvalu