Central African Republic Road Surface and Passability (2020-2024)

HeiGIT produced this dataset mapping 12,800 km of arterial roads in the Central African Republic using PlanetScope satellite imagery from 2020 and 2024. It integrates AI-derived surface predictions, width classifications, and a Humanitarian Passability Index (HPI) with existing OpenStreetMap attributes.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to identify accessible transport routes
• Infrastructure monitoring by analyzing 'Road Surface Change' to detect unpaved-to-paved transitions
• Vehicle routing using 'Road Width Class' to determine suitability for heavy truck traffic

Strengths

• 89.2% accuracy for AI-derived surface predictions
• Covers 12,800 km of the national arterial road network
• Includes multi-temporal surface change data (2020-2024)

Limitations

• Excludes local and residential road classifications
• AI-derived predictions are subject to model error compared to ground truth
• Geographic scope is limited to the Central African Republic

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

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

Time Range

2020-2024

Freshness

Last updated March 2026; temporal coverage includes imagery from 2020 and 2024.

Geography

Central African Republic