Saint Lucia Road Surface Classification from OSM and Deep Learning

A 2026 dataset from the Heidelberg Institute for Geoinformation Technology (HeiGIT) provides detailed road surface information for Saint Lucia. It classifies approximately 2 km of roads from OpenStreetMap as paved or unpaved using a hybrid deep learning model, and includes AI-derived estimates for paved (0.7 km) and unpaved (0.4 km) lengths. The data is augmented with urban classification layers and supports transportation and GIS applications.

Use Cases

• Transportation planning based on paved vs. unpaved road classifications.
• Infrastructure analysis using combined OSM and deep learning surface classifications.
• Climate emissions assessment leveraging road surface and urban/rural attributes.
• GIS applications utilizing geospatial road network data with surface and highway type attributes.

Strengths

• Integrates multiple data sources: OpenStreetMap, deep learning predictions from Mapillary imagery, and urban layers (GHSU, AFRICAPOLIS).
• Provides AI-derived estimates for road surface coverage, quantifying paved (32.16%) and unpaved (20.29%) lengths.
• Includes multiple classification fields (pred_class, osm_surface_class, combined_surface_*) for flexibility in analysis.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset notes that approximately 47.54% of road surface information is missing in the original 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

The mean timestamp of predictions used is recorded in the 'DL_mean_timestamp' field.

Freshness

Last updated 2026-03-02 17:12:15.426852; freshness should be verified.

Geography

Saint Lucia