Bonaire, Sint Eustatius and Saba: Road Surface and Passability Data

Produced by HeiGIT, this dataset provides AI-derived road surface, width, and passability metrics for arterial roads in Bonaire, Sint Eustatius, and Saba using 2020 and 2024 PlanetScope imagery. It covers approximately 100 km of the road network, integrating OpenStreetMap attributes with deep-learning predictions that achieved 89.2% accuracy.

Use Cases

• Identifying routes suitable for heavy truck traffic using 'Road Width Class 3'
• Prioritizing humanitarian logistics based on 'Humanitarian Passability Index' (HPI) scores
• Detecting infrastructure improvements by filtering for 'Road Surface Change' from unpaved to paved

Strengths

• 89.2% accuracy for AI-derived surface predictions
• Multi-temporal coverage (2020 and 2024) for change detection
• Standardized Humanitarian Passability Index (HPI) for logistics

Limitations

• Restricted to arterial road classes, omitting the majority of local road networks
• Small sample size of approximately 100 km total road length
• Potential AI prediction errors in areas with dense vegetation or cloud cover

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning analysis of PlanetScope satellite imagery integrated with OpenStreetMap road network data.

Time Range

2020-2024

Freshness

Last updated March 2026; utilizes satellite imagery from 2020 and 2024.

Geography

Bonaire, Sint Eustatius, and Saba