San Marino: Road Surface, Width, and Passability (2020-2024)

HeiGIT generated these AI-derived road surface, width, and passability metrics for San Marino's arterial road network using 2020 and 2024 PlanetScope satellite imagery. It integrates OpenStreetMap (OSM) segments with deep-learning predictions to provide consistent coverage of motorway, trunk, primary, and secondary roads. The analysis fills gaps in OSM surface tags with a model accuracy of 89.2%.

Use Cases

• Monitoring infrastructure development by identifying transitions from unpaved to paved roads using the 'Road Surface Change' indicator
• Assessing logistical constraints for heavy vehicles using 'Road Width Class' to identify segments narrower than 3.5 meters
• Prioritizing humanitarian transport routes by filtering for 'Score 1' (highest passability) in the 'Humanitarian Passability Index (HPI)' column

Strengths

• PlanetScope surface model achieved 89.2% accuracy
• Includes temporal change detection between 2020 and 2024
• Provides width classifications (Class 1-3) for logistical planning

Limitations

• Restricted to arterial road classes (motorway, trunk, primary, secondary)
• Small geographic scope of San Marino limits total road mileage
• AI-derived predictions may contain errors compared to ground-truth surveys

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

AI-derived predictions from PlanetScope satellite imagery combined with OSM road segments

Time Range

2020-2024

Freshness

Last updated March 2026; based on imagery from 2020 and 2024.

Geography

San Marino