Macao Road Surface and Passability Metrics for 200 km of Arterial Roads

HeiGIT produced this dataset of AI-derived road surface, width, and passability metrics for arterial roads in Macao SAR using 2020 and 2024 PlanetScope satellite imagery. It covers approximately 200 km of road segments, augmenting OpenStreetMap data with deep-learning predictions that fill gaps in existing surface tags.

Use Cases

• Logistics routing using the Humanitarian Passability Index (HPI) to determine accessibility for relief vehicles
• Infrastructure monitoring by identifying unpaved-to-paved transitions in the Road Surface Change (2020-2024) field
• Transportation planning using Road Width Class (1-3) to identify segments restricted to light vehicles

Strengths

• 89.2% surface prediction accuracy
• Multi-temporal comparison between 2020 and 2024
• Standardized width classes for logistical planning

Limitations

• Small geographic footprint limited to Macao SAR
• Exclusion of non-arterial road classes
• Potential urban canyon interference in satellite-derived metrics

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

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

Time Range

2020-2024

Freshness

Last updated March 2026; covers imagery from 2020 and 2024.

Geography

Macao Special Administrative Region, China