openEO
Wind turbine detection
Description
Detects wind turbines in open landscapes using Sentinel-2 imagery and a pre-trained computer vision object detection model. Open landscapes can be considered all landscapes outside of built-up urban and peri-urban areas together with forested areas. In general open landscapes is mainly comprised of open agricultural land and nature areas.
The user selects a region of interest and specifies a year to analyze. The best available Sentinel-2 imagery for the selected region is ranked based on quality metrics and the highest ranked image is chosen for wind turbine detection, based on several ranking parameters. The Sentinel-2 imagery is then passed to the pre-trained neural network that returns the bounding boxes for each detected turbine. Wind turbines are reported with a detection probability on the scale of 0 - 1. The higher the probability of the detection, the higher confidence that it is a TRUE detection.
Additional filtering is applied to account for multiple detections in close proximity. The end result includes a .geojson file defining the bounding box of all wind turbine detections with the detection date and probability as attributes. The service is so far applicable to Central Europe, with plans to expand further.
Performance characteristics
The costs of this service are based on the requested output area, making it independent of platform performance. An example run of 220km² takes up to 30 minutes to complete, while smaller test areas complete drastically faster.
Examples
Below we overlay a Sentinel2-RGB image with the ML classification, thereby highlighting the detected areas.
Known limitations
Works in open landscapes only, see description.
Execution information
-
openEO Process
-
openEO Backend
| Parameter | Type | Default |
|---|---|---|
spatial_extent (required) Limits the data to process to the specified bounding box or polygons. For raster data, the process loads the pixel into the data cube if the point at the pixel center intersects with the bounding box or any of the polygons (as defined in the Simple Features standard by the OGC). For vector data, the process loads the geometry into the data cube if the geometry is fully within the bounding box or any of the polygons (as defined in the Simple Features standard by the OGC). Empty geometries may only be in the data cube if no spatial extent has been provided. Empty geometries are ignored. Set this parameter to null to set no limit for the spatial extent. | object/bounding-box, object/datacube | |
year The year for wind turbine detection. | string | 2024 |