Morocco Arterial Roads: AI-Derived Surface, Width, and Passability Data

AI-derived infrastructure metrics for approximately 32,700 km of arterial roads in Morocco using PlanetScope satellite imagery from 2020 and 2024. Developed by the Heidelberg Institute for Geoinformation Technology (HeiGIT), it integrates OpenStreetMap (OSM) segments with deep-learning predictions for surface type, width, and logistical accessibility. The analysis focuses specifically on motorway, trunk, primary, and secondary road classes.

Use Cases

• Logistics and route planning using the Humanitarian Passability Index (HPI) to identify high-risk or narrow segments
• Infrastructure monitoring by tracking the Road Surface Change column to identify newly paved arterial segments
• Transportation capacity modeling using Road Width Class to determine if segments support two-lane heavy truck flow

Strengths

• AI surface model achieves 89.2% accuracy compared to 64.7% for standard OSM tags
• Fills surface data gaps for 31,700 km of road segments lacking OSM tags
• Includes standardized Road Width Class (1-3) for vehicle flow assessment
• Provides a temporal change indicator for infrastructure development between 2020 and 2024

Limitations

• Geographic scope is limited to Morocco's arterial network
• Predictions are AI-derived and may contain errors inherent to satellite imagery analysis
• Excludes the majority of the minor road network (residential and unclassified)

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

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

Time Range

2020 - 2024

Freshness

Uses satellite imagery from 2020 and 2024 to provide a multi-year comparison of infrastructure state.

Geography

Morocco