Saint Martin Road Surface and Passability Data (2020-2024)

HeiGIT produced this geospatial dataset providing AI-derived road surface, width, and passability metrics for arterial roads in Saint Martin (French part) using 2020 and 2024 PlanetScope imagery. It classifies motorway, trunk, primary, and secondary road segments to support humanitarian logistics and infrastructure monitoring.

Use Cases

• Evaluating heavy vehicle accessibility using the Road Width Class and Humanitarian Passability Index (HPI)
• Identifying infrastructure improvements by tracking transitions in Road Surface Change from 2020 to 2024
• Supplementing missing OpenStreetMap surface tags with DL Surface Prediction 2024 values

Strengths

• 89.2% surface prediction accuracy compared to 64.7% for standard OSM tags
• Multi-temporal surface change detection between 2020 and 2024
• Standardized width classes based on heavy truck clearance and blockage risk

Limitations

• Geographic scope is restricted to the French part of Saint Martin
• Excludes minor and residential road networks
• AI-derived predictions may contain errors in areas with dense vegetation or cloud cover

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning models applied to PlanetScope satellite imagery and integrated with OpenStreetMap road segments.

Time Range

2020 - 2024

Freshness

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

Geography

Saint Martin (French part)