Tuvalu Arterial Road Surface and Passability Metrics (2020-2024)

HeiGIT produced this dataset of AI-derived road surface, width, and passability metrics for Tuvalu's arterial road network using PlanetScope satellite imagery from 2020 and 2024. It supplements OpenStreetMap (OSM) data with deep-learning predictions for motorway, trunk, primary, and secondary road segments to fill metadata gaps.

Use Cases

• Assessing logistical accessibility for emergency response using the Humanitarian Passability Index (HPI)
• Identifying narrow infrastructure bottlenecks for heavy vehicles using the Road Width Class (1-3)
• Monitoring national infrastructure development by analyzing the Road Surface Change indicator between 2020 and 2024

Strengths

• Surface model achieved 89.2% accuracy, significantly higher than the 64.7% accuracy of standard OSM surface tags
• Provides multi-temporal surface data (2020 vs 2024) for infrastructure change detection
• Standardized width classification based on specific vehicle capacity thresholds (e.g., <3.5m, 3.5-5.5m, >5.5m)

Limitations

• Geographic scope is restricted to the small island nation of Tuvalu
• Excludes lower-tier road classifications like residential or service roads
• Relies on AI predictions which may have errors in areas with heavy cloud cover or overhanging vegetation

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

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

Time Range

2020-2024

Freshness

The dataset uses imagery from 2020 and 2024, with the last update recorded in March 2026.

Geography

Tuvalu