Dominican Republic Road Surface Classification from OSM and AI

HeiGIT's dataset provides AI-derived road surface classifications for the Dominican Republic, distinguishing paved from unpaved roads. It covers approximately 82,700 kilometers of roads mapped in OpenStreetMap, with 15% paved and 6.6% unpaved according to model predictions. The data was last updated on March 2, 2026.

Use Cases

• Transportation planning based on road surface type and length statistics.
• Infrastructure analysis using attributes like highway type, surface, and smoothness.
• Climate emissions assessment leveraging road surface data for vehicle emission models.
• GIS applications for urban and rural classification using the urban attribute.

Strengths

• Includes AI-derived surface predictions for approximately 82,700 km of roads.
• Augments OSM data with deep learning predictions from Mapillary imagery.
• Provides combined classifications that prioritize either OSM tags or deep learning outputs.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Approximately 78.4% of road surface information is reported as missing in the underlying OSM data.

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Derived from OpenStreetMap (OSM) and augmented with deep learning predictions based on Mapillary street-level imagery.

Time Range

Mean timestamp of predictions is provided (DL_mean_timestamp), but overall temporal coverage is not specified.

Freshness

Last updated 2026-03-02 17:21:02.822775; freshness should be verified.

Geography

Dominican Republic