Jersey Road Surface, Width, and Passability Data (2020-2024)

HeiGIT produced this dataset of AI-derived road surface, width, and passability metrics for approximately 200 km of arterial roads in Jersey using PlanetScope satellite imagery from 2020 and 2024. It integrates OpenStreetMap attributes with deep-learning predictions to fill data gaps, specifically targeting motorway, trunk, primary, and secondary road classes.

Use Cases

• Assessing heavy vehicle logistical constraints using the 'Road Width Class' and 'Humanitarian Passability Index'
• Monitoring infrastructure development by analyzing 'Road Surface Change' from 2020 to 2024
• Filling missing OpenStreetMap 'surface' tags using the 'DL Surface Prediction 2024' field

Strengths

• 89.2% accuracy for the PlanetScope-based surface model
• Multi-temporal coverage for 2020 and 2024 change detection
• Standardized 6-point Humanitarian Passability Index for logistics

Limitations

• Limited to high-capacity arterial roads only
• AI-derived predictions may have inherent noise compared to ground-level surveys
• Small geographic footprint focused specifically on Jersey

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

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

Time Range

2020-2024

Freshness

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

Geography

Jersey