Eswatini Road Surface and Passability Data for 1,900 km of Arterial Roads

HeiGIT produced this dataset of AI-derived road surface, width, and passability metrics for approximately 1,900 km of arterial roads in Eswatini using 2020 and 2024 PlanetScope imagery. It integrates OpenStreetMap (OSM) segments with deep-learning predictions to fill gaps in existing infrastructure data. The analysis focuses on motorway, trunk, primary, and secondary road classes.

Use Cases

• Monitoring infrastructure improvement via the 'Road Surface Change' indicator
• Logistics planning using 'Road Width Class' to determine heavy truck accessibility
• Humanitarian response routing based on the 'Humanitarian Passability Index (HPI)' scores

Strengths

• 89.2% surface model accuracy
• Multi-temporal coverage (2020 and 2024)
• Standardized width classes for heavy vehicle logistics

Limitations

• Geographic scope limited to arterial road networks
• AI-derived predictions may contain errors in densely forested areas

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Deep learning analysis of PlanetScope satellite imagery combined with OpenStreetMap road geometries.

Time Range

2020 - 2024

Freshness

Last updated March 2026; contains imagery-derived data from 2020 and 2024.

Geography

Eswatini