Albania Road Surface Classification from OpenStreetMap and AI

A dataset from 2026 provides detailed road surface information for Albania, distinguishing paved and unpaved roads. It is derived from OpenStreetMap data and augmented with AI predictions from Mapillary imagery, created by the Heidelberg Institute for Geoinformation Technology (HeiGIT). The dataset covers approximately 60,500 km of roads, with AI estimates classifying 18.9% as paved and 29.5% as unpaved.

Use Cases

• Transportation planning based on paved versus unpaved road classifications.
• Infrastructure analysis based on road attributes like surface type, smoothness, and width.
• Climate emissions assessment based on road surface data for vehicle emission modeling.
• GIS applications for routing and network analysis based on geospatial road data.

Strengths

• Integrates multiple data sources: OpenStreetMap, Mapillary imagery, and urban classification layers.
• Provides AI-derived estimates for road surfaces, quantifying paved (0.0114 million km) and unpaved (0.0178 million km) lengths.
• Includes a hybrid classification approach with fields prioritizing either OSM tags or deep learning predictions.

Limitations

• Approximately 51.7% (0.0313 million km) of road surface information is missing in the underlying OSM data.
• The AI augmentation from Mapillary imagery currently provides only 0.137% of the missing surface information.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

OpenStreetMap (OSM), augmented with deep learning predictions from Mapillary imagery and urban layers (GHSL, AFRICAPOLIS).

Collection Method

Surface classification derived using a hybrid deep learning approach, as detailed in referenced papers.

Time Range

The dataset reflects the state of OSM and associated imagery at the time of its creation.

Freshness

Last updated 2026-03 02 17:25:32.627931; freshness should be verified.

Geography

Albania