Gibraltar Road Surface and Passability with 2020-2024 AI Predictions

HeiGIT produced this dataset of AI-derived road surface, width, and passability metrics for Gibraltar's arterial roads using PlanetScope satellite imagery from 2020 and 2024. It classifies motorway, trunk, primary, and secondary road segments to provide a Humanitarian Passability Index (HPI) for logistical planning.

Use Cases

• Logistical route planning for heavy vehicles using 'Road Width Class' and 'Humanitarian Passability Index (HPI)'
• Monitoring urban development by identifying 'Road Surface Change' from unpaved to paved states
• Augmenting OpenStreetMap data where the 'surface tag' is missing using AI-derived predictions

Strengths

• AI surface model achieves 89.2% accuracy compared to 64.7% for standard OSM tags
• Includes temporal change detection for road paving between 2020 and 2024
• Standardized width classification based on heavy truck flow capacity

Limitations

• Small geographic footprint of Gibraltar results in low total road mileage
• Predictions are derived from satellite imagery and may contain deep-learning classification errors
• Excludes the majority of the local road network

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

Last updated March 2026; utilizes satellite imagery from 2020 and 2024.

Geography

Gibraltar