Australia Road Surface and Passability: 190,600 km of Arterial Routes

HeiGIT produced this dataset covering 190,600 km of Australian arterial roads using AI analysis of PlanetScope satellite imagery from 2020 and 2024. It provides deep-learning predictions for road surface, width, and a Humanitarian Passability Index (HPI) to fill gaps in OpenStreetMap data.

Use Cases

• Monitoring infrastructure upgrades by identifying segments that transitioned from unpaved to paved via the Road Surface Change (2020-2024) field
• Logistics routing for heavy machinery using Road Width Class to distinguish between single-lane and two-lane heavy truck capacity
• Emergency response planning using the Humanitarian Passability Index (HPI) to identify segments with high blockage risks

Strengths

• 89.2% accuracy for surface model predictions
• Covers 190,600 km of arterial road segments
• Temporal comparison between 2020 and 2024 imagery

Limitations

• Restricted to arterial road classes, omitting the local road network
• Potential for AI misclassification in regions with dense vegetation overhanging roads

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

AI-derived analysis of PlanetScope satellite imagery integrated with OpenStreetMap data

Time Range

2020-2024

Freshness

Last updated March 2026; contains multi-temporal imagery analysis from 2020 and 2024.

Geography

Australia