Seychelles Road Surface and Passability Metrics for 100 km of Arterials

Seychelles arterial road network data featuring AI-predicted surface types and passability metrics derived from 2020 and 2024 PlanetScope imagery. Created by HeiGIT, the dataset covers approximately 100 km of motorway, trunk, primary, and secondary road segments to fill gaps in OpenStreetMap (OSM) attributes.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to identify high-risk blockage zones
• Infrastructure monitoring by analyzing Road Surface Change (2020-2024) to detect transition from unpaved to paved
• Heavy vehicle routing using Road Width Class to identify segments supporting two-lane flow (>5.5 m)

Strengths

• 89.2% accuracy for AI-derived surface model
• Fills surface tag gaps for 47% of the OSM arterial network
• Includes multi-temporal change detection (2020-2024)
• Standardized Humanitarian Passability Index (HPI) for logistics

Limitations

• Small geographic sample size of approximately 100 km total road length
• Restricted to high-capacity arterial roads only
• AI-derived predictions may contain errors compared to ground-truth surveys

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning inference on PlanetScope satellite imagery combined with OpenStreetMap road geometries

Time Range

2020 - 2024

Freshness

Based on satellite imagery from 2020 and 2024; last updated March 2026.

Geography

Seychelles