Zambia Arterial Road Surface, Width, and Passability (2020-2024)

This dataset maps approximately 11,600 km of arterial roads in Zambia, providing AI-derived surface types, widths, and passability scores generated by HeiGIT from 2020 and 2024 PlanetScope satellite imagery. It covers motorway, trunk, primary, and secondary road classes, filling data gaps for over 1,200 km of the network where OpenStreetMap surface tags were previously missing.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to identify routes capable of supporting heavy truck flow
• Infrastructure monitoring by tracking 'Road Surface Change' to identify segments upgraded from unpaved to paved
• Transport capacity assessment using 'Road Width Class' to determine if segments support unimpeded two-lane heavy vehicle traffic

Strengths

• 89.2% accuracy for surface model predictions
• Provides surface data for 92.5% of segments missing tags in OpenStreetMap
• Includes multi-temporal comparisons to identify road improvements

Limitations

• AI-derived predictions may have localized errors compared to ground-truth surveys
• Geographic scope is limited to the national arterial network of Zambia

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Deep learning analysis of PlanetScope satellite imagery integrated with OpenStreetMap vector data

Time Range

2020-2024

Freshness

Imagery analysis covers the period from 2020 to 2024; last updated in March 2026.

Geography

Zambia