New Zealand Arterial Road Surface and Passability Data (2020-2024)

HeiGIT produced this dataset covering approximately 19,000 km of New Zealand's arterial road network using PlanetScope satellite imagery from 2020 and 2024. It features AI-derived road surface types, width classifications, and a Humanitarian Passability Index (HPI) to assess logistical accessibility across the country's primary transportation backbone.

Use Cases

• Monitoring infrastructure upgrades by identifying 'Road Surface Change' from unpaved to paved between 2020 and 2024
• Emergency logistics routing using the 'Humanitarian Passability Index (HPI)' to avoid low-accessibility segments
• Fleet management planning using 'Road Width Class' to ensure heavy trucks only use Class 3 segments

Strengths

• 89.2% accuracy for surface model predictions compared to 64.7% for OSM tags
• Temporal change detection between 2020 and 2024
• Standardized width classes (1-3) for vehicle capacity assessment

Limitations

• Geographic scope limited to arterial road classes only
• AI-derived predictions have a documented 10.8% error margin
• Small percentage (0.14%) of roads lack original OSM surface tags for comparison

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning analysis of PlanetScope satellite imagery combined with OpenStreetMap data

Time Range

2020-2024

Freshness

Contains imagery-derived data from 2020 and 2024; last updated in March 2026.

Geography

New Zealand