DeepOWT v4.25.1: Deep Learning Derived, Dense Sentinel-1 Time Series for Offshore Wind Infrastructure

Unofficial AI-generated summary based on the public title and abstract. Not an official translation.

🔬研究者:Provides a ready-to-use dataset and benchmarks for developing AI models to monitor renewable energy infrastructure.

🏢実務担当者:Useful for asset managers and energy companies to track offshore wind farm construction and operational status without ground surveys.

🏛政策担当者:Enables independent, transparent monitoring of national offshore wind deployment targets.

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 dynamics on a global scale. Locations are derived by applying deep learning based object detection on ESA's spaceborne Sentinel-1 synthetic aperture radar (SAR) archive, see Global Offshore Wind Infrastructure: Deployment and Operational Dynamics from Dense Sentinel-1 Time Series Dense time series are derived by inspecting each available Sentinel-1 scene at every detected infrastructure location. One-dimensional swath profiles are generated for each acquisition and infrastructure location, showing the maximum SAR backscatter value along the horizontal axis (range direction), thereby capturing directed SAR signatures. With version v4.25.1 the data set is reorganised into three thematic groups ( spatial/ , temporal/ , training/ ) and the dense time series is enriched with deep learning derived event predictions, ensenmble event predictions fusing baseline and deep learning results recommended class labels for downstream analysis and deployment event flags indicating start and end of a deployment phase. In addition, machine-learning-ready data sets for self-supervised pre-training and supervised training are published. Related publications: Publication Data set version Added feature DeepOWT: a global offshore wind turbine data set derived with deep learning from Sentinel-1 data v1.21.2 Global OWT locations 2016Q3 - 2021Q2 hand labeld test locations North Sea Basin, and East China Sea for 2021Q2 Global Offshore Wind Infrastructure: Deployment and Operational Dynamics from Dense Sentinel-1 Time Series v3.25.1 Global OWT locations 2016Q1 - 2025Q1 hand labeld test locations North Sea Basin, East China Sea, and South East Vietnam for 2025Q1 1D SAR profile time series of all S-1 acquisition for each location + automatically derived semantic labels + hand labeled benchmark set Benchmarking Deep Learning Models for Dense Event Classification of Offshore Wind Infrastructure in Sentinel-1 Time Series (submitted 30.06.2026) v4.25.1 reorganised distribution into spatial/ , temporal/ , and training/ groups dense 1D SAR profile time series enriched with deep learning event predictions (BiLSTM model, and BiLSTM + baseline (v3.25.1) ensemble) recommended class labels for downstream analysis , and per-unit deployment start/end event flags machine-learning-ready training data sets for self-supervised pre-training and supervised training (monotemporal samples and uni-/bidirectional sequence windows) The dense event classification distinguishes seven semantic states of an infrastructure location over time: water , vessel , platform , turbine foundation , mooring / active construction , and deployed turbine ; the hand-labelled benchmark additionally uses unclear for ambiguous acquisitions. File metadata File(s) Time Geometry Spatial extent Temporal resolution spatial/DeepOWT_pnt_locations.parquet (Derived Locations, 15,606 units) 2025Q1 points Global quarterly spatial/location_validation_2025Q1.parquet (Ground Truth Location, 9,770 polygons) 2025Q1 polygons North Sea Basin, East China Sea, Southeast Vietnam - temporal/deepowt_time_series.parquet (Analysis Ready Time Series, Derived Baseline & Deep Learning Labels, Benchmark Labels, and Deployment Event Flags) 2016Q1-2025Q1 - (index into DeepOWT points via unit_id) - for each available S1-acquisition (~1-12 days) training/training_monotemporal.parquet, training/training_windows_unidirectional.parquet, training/training_windows_bidirectional.parquet (Supervised Training Samples) 2016Q1-2025Q1 - (index into temporal/deepowt_time_series.parquet via unit_id / sequence_id) - - training/ssl_monotemporal.parquet, training/ssl_windows_unidirectional.parquet, training/ssl_windows_bidirectional.parquet (Self-Supervised Pre-training Samples) 2016Q1-2025Q1 - (index into temporal/deepowt_time_series.parquet via unit_id / sequence_id) - - Column description of temporal/deepowt_time_series.parquet Column Type Description unit_id string Infrastructure location identifier; joins to spatial/DeepOWT_pnt_locations.parquet. acquisition_date string Acquisition timestamp of the Sentinel-1 scene (ISO 8601). orbit_direction string Sentinel-1 orbit direction (ascending / descending). swath_profile_horizontal_max array of double One-dimensional swath profile of maximum SAR backscatter along the horizontal axis. sequence_id integer Zero-based position of the acquisition within the unit's chronological time series. baseline_label string Event label from the rule-based baseline classifier. bilstm_label string Event label predicted by the BiLSTM deep learning model. ensemble_label string Final ensemble event label used for the deployment analysis. ensemble_source string Which model provided the ensemble label for this row (baseline or bilstm). gold_label string Hand-labelled ground-truth event label. Contains both test and train labels. is_test boolean True for acquisitions belonging to the hand-labelled benchmark test set. Use to create hold out test (benchmark) subset from gold_label is_depl_start boolean True on the single event marking the start of the unit's deployment phase. is_depl_end boolean True on the single event marking the end of the unit's deployment phase (first confirmed deployed turbine). Column description of the training data sets File group Columns Description *_monotemporal.parquet unit_id, sequence_id Single 1D swath profiles, referenced into temporal/deepowt_time_series.parquet via (unit_id, sequence_id). *_windows_unidirectional.parquet, *_windows_bidirectional.parquet unit_id, start_id, end_id, change_sequence_id, from_label, to_label, is_synth_regression Sequence windows spanning start_id..end_id with a label change at change_sequence_id (from_label to to_label). Unidirectional windows end ~at the change; bidirectional windows extend around it. is_synth_regression flags synthetically generated regression samples. The training/* files provide the labelled samples used for supervised training; the training/ssl_* files provide the (label-free with respect to human annotation) samples used for self-supervised pre-training. Both index into the dense time series temporal/deepowt_time_series.parquet.  

• Zenodo https://zenodo.org/records/21103038first seen 2026-07-02 04:14:58 · last seen 2026-07-02 04:16:59