Greenland Road Surface Classification from OpenStreetMap and AI

Approximately 2.5 kilometers of roads are mapped in OpenStreetMap for Greenland. This dataset, created by the Heidelberg Institute for Geoinformation Technology (HeiGIT), classifies these roads as paved or unpaved using a hybrid deep learning approach based on Mapillary imagery and urban layers. It was last updated on March 2, 2026.

Use Cases

• Transportation planning based on road surface type and length statistics.
• Infrastructure analysis based on attributes like highway type, surface, and width.
• Climate emissions assessment based on the proportion of paved versus unpaved roads.
• GIS applications for routing and accessibility based on geospatial road data.
• Validating and augmenting OpenStreetMap data based on AI-derived surface predictions.

Strengths

• Provides AI-derived surface classification for approximately 2.5 km of roads.
• Integrates multiple data sources: OpenStreetMap, Mapillary imagery, and urban settlement layers.
• Includes detailed OSM and urban classification attributes for contextual analysis.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count is unknown, which may limit suitability assessment.
• About 1.4 km (56.74%) of road surface information is missing in the original OSM data.

Provenance

Source

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

Collection Method

Surface classification derived using a hybrid deep learning approach.

Time Range

null

Freshness

Last updated 2026-03-02 17:05:13.439825; freshness should be verified.

Geography

Greenland