Lesotho Road Surface and Passability Data for 2,100 km of Arterial Roads

AI-derived road surface, width, and passability metrics for approximately 2,100 km of arterial roads in Lesotho, produced by HeiGIT using 2020 and 2024 PlanetScope imagery. The data integrates OpenStreetMap (OSM) attributes with deep-learning predictions to fill gaps in existing infrastructure records and assess logistical accessibility.

Use Cases

• Monitoring infrastructure development by tracking 'Road Surface Change' from 2020 to 2024
• Logistics planning using the 'Humanitarian Passability Index (HPI)' to identify high-risk blockage areas
• Route optimization for heavy vehicles based on 'Road Width Class' (1-3) to ensure unimpeded flow

Strengths

• 89.2% accuracy for AI-derived surface model predictions
• Multi-temporal coverage (2020 and 2024) enabling road surface change detection
• Standardized width classification (Class 1-3) based on physical vehicle clearance

Limitations

• Geographic focus is limited to the arterial road backbone
• AI-derived predictions may contain errors compared to ground-level surveys
• OSM surface tags were only available for 64.7% of segments in the comparison model

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Deep learning analysis of PlanetScope satellite imagery integrated with OpenStreetMap road network data.

Time Range

2020-2024

Freshness

Last updated March 2026; imagery analysis covers the period between 2020 and 2024.

Geography

Lesotho