Malawi Road Surface and Passability Data for 6,200 km of Arterial Roads

HeiGIT produced this geospatial dataset covering 6,200 km of arterial roads in Malawi with AI-derived surface and width attributes. It utilizes PlanetScope satellite imagery from 2020 and 2024 to classify motorways, trunks, and primary/secondary roads. The data fills significant gaps in existing OpenStreetMap records where surface information is missing.

Use Cases

• Assessing logistical accessibility for heavy vehicles using the 'Road Width Class' and 'Humanitarian Passability Index (HPI)'
• Monitoring infrastructure development by analyzing 'Road Surface Change' between 2020 and 2024
• Filling data gaps in OpenStreetMap by integrating 'DL Surface Prediction 2024' where 'surface tag' is missing

Strengths

• 89.2% accuracy for road surface predictions
• Multi-temporal coverage (2020 and 2024) for change detection
• Standardized Humanitarian Passability Index (HPI) scoring from 1 to 6

Limitations

• Excludes residential and unclassified local roads, focusing only on arterial networks
• AI-derived predictions may contain errors in areas with dense canopy or cloud cover

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

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

Time Range

2020-2024

Freshness

Based on 2024 imagery; last updated March 2026.

Geography

Malawi