Bulgaria Road Surface and Passability: 10,900 km of AI-Derived Metrics

Delivering AI-derived surface types, widths, and passability scores for approximately 10,900 km of arterial roads in Bulgaria. Created by the Heidelberg Institute for Geoinformation Technology (HeiGIT), it utilizes PlanetScope satellite imagery from 2020 and 2024 to augment OpenStreetMap (OSM) data. The analysis focuses on motorways, trunks, and primary/secondary roads that form the national transportation backbone.

Use Cases

• Logistics and emergency response planning using the Humanitarian Passability Index (HPI) to identify accessibility constraints
• Infrastructure monitoring by tracking the Road Surface Change column to identify newly paved segments
• Heavy vehicle routing optimization using Road Width Class to avoid narrow segments (Class 1 <3.5m)

Strengths

• 89.2% surface model accuracy, significantly higher than the 64.7% accuracy of standard OSM surface tags
• Provides surface information for 1,700 km of roads that lack tags in OpenStreetMap
• Includes multi-temporal analysis (2020 vs 2024) to identify infrastructure improvements

Limitations

• Geographic scope is limited to Bulgaria's arterial network
• Width classifications are grouped into three broad categories rather than precise meter measurements
• Surface change detection only identifies transitions from unpaved to paved

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Deep learning models applied to PlanetScope satellite imagery integrated with OpenStreetMap road geometries.

Time Range

2020 - 2024

Freshness

Contains imagery-derived data from 2020 and 2024; last updated in March 2026.

Geography

Bulgaria