DeepOWT: A global offshore wind turbine data set

DeepOWT (deep learning derived global offshore wind turbines) is an independent and openly accessible data set of offshore wind energy infrastructure locations and their temporal deployment dynamics on a global scale. It is derived by applying deep learning based object detection on ESA's spaceborne Sentinel-1 synthetic aperture radar (SAR) archive. DeepOWT provides OWT locations along with their quarterly deployment stages from 2016 until 2021. It differentiates between platforms under construction, OWTs which are readily deployed and offshore wind farm substations, such as transformer stations. Related publication File metadata File Time Periods Geometry Entries DeepOWT.geojson (Dataset) 2016Q3-2021Q2 20 points 9941 gt_2021Q2_nsb.geojson (Ground Truth) 2021Q2 1 polygons 4354 gt_2021Q2_ecs.geojson (Ground Truth) 2021Q2 1 polygons 2844 gt_2019Q4_nsb.geojson (Ground Truth) 2019Q4 1 polygons 3821 gt_2019Q4_ecs.geojson (Ground Truth) 2019Q4 1 polygons 1469 gt_2016Q3-2021Q1_nsb.geojson (GT) 2016Q3-2021Q1 19 polygons 650 gt_2016Q3-2021Q1_ecs.geojson (GT) 2016Q3-2021Q1 19 polygons 430 gt_nsb_gridded.geojson (GT North Sea Basin) polygon 1 gt_ecs_gridded.geojson (GT East China Sea) polygon 1 Mapping of integer values used in the dataset to semantic classes Integer Semantic label Abbreviation 0 open sea sea 1 under construction const 2 offshore wind turbine owt 3 offshore wind farm substation sub