U.S. Virgin Islands Road Surface and Passability Data (2020-2024)

Supplying AI-derived road surface, width, and passability metrics for approximately 300 km of arterial roads in the United States Virgin Islands. Created by the Heidelberg Institute for Geoinformation Technology (HeiGIT), the data utilizes PlanetScope satellite imagery from 2020 and 2024 to enhance OpenStreetMap (OSM) records.

Use Cases

• Assessing logistical constraints for heavy trucks using the Road Width Class and Humanitarian Passability Index
• Monitoring infrastructure development by comparing DL Surface Prediction 2020 and 2024 to identify unpaved-to-paved transitions
• Filling gaps in OpenStreetMap by identifying segments where the surface tag is null and replacing it with AI-derived predictions

Strengths

• High surface classification accuracy of 89.2% compared to 64.7% for existing OSM tags
• Includes multi-temporal data (2020 and 2024) allowing for change detection
• Provides standardized road width classifications (Class 1-3) based on vehicle capacity

Limitations

• Limited to arterial roads, excluding residential and local streets
• Small geographic footprint covering only the United States Virgin Islands
• Potential for AI misclassification in areas with dense canopy or cloud cover

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

AI-derived predictions from PlanetScope satellite imagery integrated with OpenStreetMap (OSM) attributes

Time Range

2020-2024

Freshness

Last updated March 2026; contains imagery-derived data from 2020 and 2024.

Geography

United States Virgin Islands