Dataset according to "A Wind Turbines Dataset for South Africa: Open Street Map Data, Deep Learning Based Geo-Coordinate Correction and Capacity Analysis"

Dataset Summary
This dataset provides the most accurate and comprehensive geospatial information on wind turbines in South Africa as of 2025. It includes precise turbine coordinates, detailed technical attributes, and spatially harmonized metadata across 42 wind farms. The dataset contains 1,487 individual turbine entries with validated information on turbine type, rated capacity, rotor diameter, commissioning year, and administrative regions. It was compiled by integrating OpenStreetMap (OSM) data, satellite imagery from Google and Bing, a RetinaNet-based deep learning model for coordinate correction, and manual verification.

Data Structure

• Format: GeoJSON

• Coordinate Reference System (CRS): WGS 84 (EPSG:4326)

• Number of features: 1,487

• Geometry type: Point (turbine locations)

• Key attributes:

  • id: Unique internal identifier

  • osm_id: Reference ID from OpenStreetMap

  • gid, country, type1, name1, type2, name2: Administrative region (based on GADM)

  • farm_name: Name of the wind farm

  • commissioning_year: Year the turbine was commissioned

  • number_of_turbines: Total number of turbines at the wind farm

  • total_farm_capacity: Total installed capacity of the wind farm (MW)

  • capacity_per_turbine: Rated power per turbine (MW)

  • turbine_type: Manufacturer and model of the turbine

  • geometry: Point geometry (longitude, latitude)

Publication Abstract
Accurate and detailed spatial data on wind energy infrastructure is essential for renewable energy planning, grid integration, and system analysis. However, publicly available datasets often suffer from limited spatial accuracy, missing attributes, and inconsistent metadata. To address these challenges, this study presents a harmonized and spatially refined dataset of wind turbines in South Africa, combining OpenStreetMap (OSM) data with high-resolution satellite imagery, deep learning-based coordinate correction, and manual curation. The dataset includes 1487 turbines across 42 wind farms, representing over 3.9 GW of installed capacity as of 2025. Of this, more than 3.6 GW is currently operational. The Geo-Coordinates were validated and corrected using a RetinaNet-based object detection model applied to both Google and Bing satellite imagery. Instead of relying solely on spatial precision, the curation process emphasized attribute completeness and consistency. Through systematic verification and cross-referencing with multiple public sources, the final dataset achieves a high level of attribute completeness and internal consistency across all turbines, including turbine type, rated capacity, and commissioning year. The resulting dataset is the most accurate and comprehensive publicly available dataset on wind turbines in South Africa to date. It provides a robust foundation for spatial analysis, energy modeling, and policy assessment related to wind energy development. The dataset is publicly available.

Citation Notification

If you use this dataset, please cite the following publication (currently in the process of publication):

Kleebauer, M.; Karamanski, S.; Callies, D.; Braun, M. A Wind Turbines Dataset for South Africa: OpenStreetMap Data, Deep Learning Based Geo-Coordinate Correction and Capacity Analysis. ISPRS Int. J. Geo-Inf. 2025, 14, 232. https://doi.org/10.3390/ijgi14060232