Nigeria Arterial Road Surface and Passability: 61,900 km AI-Derived Data

HeiGIT produced this dataset mapping 61,900 km of Nigerian arterial roads using AI analysis of PlanetScope satellite imagery from 2020 and 2024. It provides surface type, width, and passability metrics for motorways, trunk, primary, and secondary road segments, filling significant gaps in existing OpenStreetMap data.

Use Cases

• Monitoring infrastructure progress by identifying segments where 'Road Surface Change' indicates a transition from unpaved to paved between 2020 and 2024
• Optimizing humanitarian supply chains by filtering for 'Humanitarian Passability Index (HPI)' Score 1 to ensure unimpeded heavy vehicle access
• Evaluating road capacity for logistics planning using 'Road Width Class' to distinguish between single-lane and two-lane heavy truck flow

Strengths

• 89.2% accuracy for AI-derived surface predictions, significantly higher than the 64.7% accuracy of OSM surface tags
• Includes temporal change detection for road surfacing over a four-year period
• Standardized width classification (Class 1-3) based on heavy vehicle passability

Limitations

• Excludes local and residential road classes, focusing only on the arterial backbone
• AI-derived predictions are subject to interpretation errors from satellite imagery compared to ground-level surveys

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning models applied to PlanetScope satellite imagery (2020 and 2024) integrated with OpenStreetMap road geometries.

Time Range

2020 - 2024

Freshness

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

Geography

Nigeria