Anguilla Road Surface, Width, and Passability Metrics (2020-2024)

Anguilla arterial road network data featuring AI-derived surface types, widths, and passability scores for approximately 100 kilometers of infrastructure. Created by HeiGIT, the dataset utilizes PlanetScope satellite imagery from 2020 and 2024 to augment OpenStreetMap attributes with deep-learning predictions. It specifically targets motorway, trunk, primary, and secondary road classifications.

Use Cases

• Logistics planning for heavy vehicle transport using the Road Width Class (1-3) and Humanitarian Passability Index (HPI)
• Infrastructure monitoring to identify transitions from unpaved to paved surfaces via the Road Surface Change attribute
• Enhancing OpenStreetMap data quality by filling missing surface tags with DL Surface Prediction values

Strengths

• Surface model accuracy of 89.2% significantly exceeds the 64.7% accuracy of existing OSM surface tags
• Dual-epoch imagery (2020 and 2024) enables temporal analysis of road improvements
• Standardized width classification based on specific vehicle clearance thresholds (<3.5m, 3.5-5.5m, >5.5m)

Limitations

• Small sample size reflecting the limited road network of Anguilla (approx. 100km)
• Geographic bias towards arterial roads, omitting the majority of the local road network
• Potential for AI-derived prediction errors in surface and width classification

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology) using PlanetScope satellite imagery

Collection Method

Deep-learning predictions generated from satellite imagery integrated with OpenStreetMap vector data

Time Range

2020-2024

Freshness

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

Geography

Anguilla