Jordan Road Surface and Passability Data for 6,700 km of Arterial Roads

This dataset maps approximately 6,700 km of arterial roads in Jordan, providing AI-derived surface types and width classifications generated by HeiGIT from 2020 and 2024 PlanetScope satellite imagery. It integrates OpenStreetMap attributes with deep-learning predictions to assess road passability for humanitarian logistics across motorway, trunk, primary, and secondary road classes.

Use Cases

• Monitoring national infrastructure development by analyzing the 'Road Surface Change' column to identify newly paved segments
• Optimizing humanitarian delivery routes using the 'Humanitarian Passability Index (HPI)' to avoid low-passability corridors
• Identifying vehicle size restrictions for logistics using 'Road Width Class' to determine if segments support two-lane heavy trucks

Strengths

• 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 Humanitarian Passability Index (HPI) for logistical planning

Limitations

• Analysis is restricted to arterial roads and excludes local or residential street networks
• Road Width Class is a categorical estimate (1-3) rather than a continuous meter measurement
• Satellite-derived predictions may have reduced accuracy in areas with significant cloud cover or shadows

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT) using PlanetScope imagery

Collection Method

Deep learning models applied to 3-meter resolution satellite imagery integrated with OpenStreetMap vector data

Time Range

2020 - 2024

Freshness

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

Geography

Jordan