DeepOWT: a global offshore wind turbine data set derived with deep learning from Sentinel-1 data

Abstract. Offshore wind energy is at the advent of a massive global expansion. To investigate the development of the offshore wind energy sector, optimal offshore wind farm locations, or the impact of offshore wind farm projects, a freely accessible spatiotemporal data set of offshore wind energy infrastructure is necessary. With free and direct access to such data, it is more likely that all stakeholders who operate in marine and coastal environments will become involved in the upcoming massive expansion of offshore wind farms. To that end, we introduce the DeepOWT (Deep-learning-derived Offshore Wind Turbines) data set (available at https://doi.org/10.5281/zenodo.5933967, Hoeser and Kuenzer, 2022b), which provides 9941 offshore wind energy infrastructure locations along with their deployment stages on a global scale. DeepOWT is based on freely accessible Earth observation data from the Sentinel-1 radar mission. The offshore wind energy infrastructure locations were derived by applying deep-learning-based object detection with two cascading convolutional neural networks (CNNs) to search the entire Sentinel-1 archive on a global scale. The two successive CNNs have previously been optimised solely on synthetic training examples to detect the offshore wind energy infrastructures in real-world imagery. With subsequent temporal analysis of the radar signal at the detected locations, the DeepOWT data set reports the deployment stages of each infrastructure with a quarterly frequency from July 2016 until June 2021. The spatiotemporal information is compiled in a ready-to-use geographic information system (GIS) format to make the usability of the data set as accessible as possible.

[1]  S. Maxwell,et al.  Offshore renewables need an experimental mindset , 2022, Science.

[2]  C. Kuenzer,et al.  SyntEO: Synthetic Dataset Generation for Earth Observation with Deep Learning - Demonstrated for Offshore Wind Farm Detection , 2021, ISPRS Journal of Photogrammetry and Remote Sensing.

[3]  Y. Si,et al.  Global offshore wind turbine dataset , 2021, Scientific data.

[4]  Francesca Bovolo,et al.  CNN-based burned area mapping using radar and optical data , 2021, Remote Sensing of Environment.

[5]  Sina Montazeri,et al.  Deep Learning Meets SAR: Concepts, models, pitfalls, and perspectives , 2021, IEEE Geoscience and Remote Sensing Magazine.

[6]  Sergio L. Netto,et al.  A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit , 2021, Electronics.

[7]  Claudia Kuenzer,et al.  A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep Learning , 2021, Remote. Sens..

[8]  A. Faaij,et al.  Spatial and temporal analysis of cumulative environmental effects of offshore wind farms in the North Sea basin , 2020, Scientific Reports.

[9]  Yongchao Liu,et al.  Proliferation of offshore wind farms in the North Sea and surrounding waters revealed by satellite image time series , 2020 .

[10]  Claudia Kuenzer,et al.  Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review - Part II: Applications , 2020, Remote. Sens..

[11]  Thorsten Hoeser,et al.  Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends , 2020, Remote. Sens..

[12]  Johannes L. Schönberger,et al.  Author Correction: SciPy 1.0: fundamental algorithms for scientific computing in Python , 2020, Nature Methods.

[13]  Claudia Yamu,et al.  A Spatial Analysis of the Potentials for Offshore Wind Farm Locations in the North Sea Region: Challenges and Opportunities , 2020, ISPRS Int. J. Geo Inf..

[14]  Dino Ienco,et al.  Distilling Before Refine: Spatio-Temporal Transfer Learning for Mapping Irrigated Areas Using Sentinel-1 Time Series , 2020, IEEE Geoscience and Remote Sensing Letters.

[15]  Patrick N. Halpin,et al.  Automating offshore infrastructure extractions using synthetic aperture radar & Google Earth Engine , 2019, Remote Sensing of Environment.

[16]  Celia A. Baumhoer,et al.  Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning , 2019, Remote. Sens..

[17]  Joel Nothman,et al.  SciPy 1.0-Fundamental Algorithms for Scientific Computing in Python , 2019, ArXiv.

[18]  F. Cumo,et al.  Wind energy potential analysis using Sentinel-1 satellite: A review and a case study on Mediterranean islands , 2019, Renewable and Sustainable Energy Reviews.

[19]  Lei Ma,et al.  Deep learning in remote sensing applications: A meta-analysis and review , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[20]  Prabhat,et al.  Deep learning and process understanding for data-driven Earth system science , 2019, Nature.

[21]  Jing Zhang,et al.  Automatic Extraction of Offshore Platforms in Single SAR Images Based on a Dual-Step-Modified Model , 2019, Sensors.

[22]  Raul Queiroz Feitosa,et al.  Dense Fully Convolutional Networks for Crop Recognition from Multitemporal SAR Image Sequences , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[23]  Valentyn Tolpekin,et al.  Fully Convolutional Networks for Multi-Temporal SAR Image Classification , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[24]  Michael Dixon,et al.  Google Earth Engine: Planetary-scale geospatial analysis for everyone , 2017 .

[25]  Xiao Xiang Zhu,et al.  Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources , 2017, IEEE Geoscience and Remote Sensing Magazine.

[26]  Kai W. Wirtz,et al.  The large-scale impact of offshore wind farm structures on pelagic primary productivity in the southern North Sea , 2017, Hydrobiologia.

[27]  Zhao Lin,et al.  Contextual Region-Based Convolutional Neural Network with Multilayer Fusion for SAR Ship Detection , 2017, Remote. Sens..

[28]  Frank Hutter,et al.  SGDR: Stochastic Gradient Descent with Warm Restarts , 2016, ICLR.

[29]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[30]  A. G. Dutton,et al.  An Offshore Wind Energy Geographic Information System (OWE-GIS) for assessment of the UK's offshore wind energy potential , 2016 .

[31]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Pavol Bauer,et al.  Trends of offshore wind projects , 2015 .

[33]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[35]  Helen Bailey,et al.  Assessing environmental impacts of offshore wind farms: lessons learned and recommendations for the future , 2014, Aquatic biosystems.

[36]  Dan Wilhelmsson,et al.  Effects of offshore wind farms on marine wildlife—a generalized impact assessment , 2014 .

[37]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[38]  Malcolm Davidson,et al.  GMES Sentinel-1 mission , 2012 .

[39]  Vicente Negro,et al.  Why offshore wind energy , 2011 .

[40]  Michael Elliott,et al.  The Habitat-Creation Potential of Offshore Wind Farms , 2009, Renewable Energy.

[41]  R. Langston,et al.  Assessing the impacts of wind farms on birds , 2006 .

[42]  Thomas Kjær Christensen,et al.  Information needs to support environmental impact assessment of the effects of European marine offshore wind farms on birds , 2006 .

[43]  Josef Aschbacher,et al.  ESA’s Earth Observation Strategy and Copernicus , 2017 .

[44]  Bela H. Buck,et al.  Lessons from stakeholder dialogues on marine aquaculture in offshore wind farms: Perceived potentials, constraints and research gaps , 2015 .

[45]  Rebecca J. Barthelmie,et al.  Offshore Wind Energy in Europe— A Review of the State‐of‐the‐Art , 2003 .

[46]  Robert Altenloh.  From a Novel , 1953 .