U.S. Virgin Islands Road Surface Classification from OSM and AI

United States Virgin Islands road network data provides detailed surface classifications, distinguishing paved from unpaved roads. The dataset originates from OpenStreetMap and is augmented with deep learning predictions based on Mapillary imagery and urban layers from GHSU and AFRICAPOLIS. It was last updated on March 2, 2026, by the Heidelberg Institute for Geoinformation Technology (HeiGIT).

Use Cases

• Transportation planning based on road surface type and urban classification attributes.
• Infrastructure analysis based on OSM attributes like highway type, surface, and width.
• Climate emissions assessment based on paved versus unpaved road network composition.
• GIS applications for routing and logistics based on geospatial road network data.

Strengths

• Includes AI-derived surface classifications (pred_class, pred_label) from a hybrid deep learning approach.
• Combines multiple data sources: OSM tags, Mapillary imagery, and urban layers (GHSU 2019, AFRICAPOLIS 2020).
• Provides multiple classification schemes (OSM-priority, DL-priority) for flexibility in analysis.

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.
• Key statistics (total road length, paved/unpaved percentages) are reported as 0.0 million km and nan%, indicating missing or placeholder values.

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Data originates from OpenStreetMap, augmented with deep learning predictions from Mapillary street-level imagery and combined with urban classification layers.

Time Range

null

Freshness

Last updated 2026-03-02 17:18:58.644635; freshness should be verified.

Geography

United States Virgin Islands