Botswana Road Surface and Passability: 8,700 km of Arterial Roads

HeiGIT produced this dataset of AI-derived road surface, width, and passability metrics for approximately 8,700 km of arterial roads in Botswana using 2020 and 2024 PlanetScope imagery. It supplements OpenStreetMap data by providing surface predictions for segments previously lacking surface tags, covering motorways, trunks, primary, and secondary roads.

Use Cases

• Logistics planning using the 'Humanitarian Passability Index' to identify high-capacity transport routes
• Infrastructure monitoring via 'Road Surface Change' to detect transitions from unpaved to paved roads
• Vehicle-specific routing using 'Road Width Class' to determine suitability for heavy trucks versus light vehicles

Strengths

• 89.2% accuracy for road surface model predictions
• Covers 8,700 km of arterial road network
• Multi-temporal change detection between 2020 and 2024

Limitations

• Geographic scope is limited to Botswana
• Excludes minor and residential road classes
• AI-derived predictions may contain errors compared to ground-truth surveys

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

AI-derived predictions from PlanetScope satellite imagery integrated with OpenStreetMap road geometries.

Time Range

2020-2024

Freshness

Based on satellite imagery from 2020 and 2024; last updated March 2026.

Geography

Botswana