A new gridded offshore wind profile product for US coasts using machine learning and satellite observations
<p>Offshore wind speed data around wind turbine hub heights are fairly limited, available through in situ observations from wind masts, sonic detection and ranging (sodar) instruments, or floating light detection and ranging (lidar) buoys at selected locations or as forecasting-model-based ou...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-06-01
|
| Series: | Wind Energy Science |
| Online Access: | https://wes.copernicus.org/articles/10/1077/2025/wes-10-1077-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | <p>Offshore wind speed data around wind turbine hub heights are fairly limited, available through in situ observations from wind masts, sonic detection and ranging (sodar) instruments, or floating light detection and ranging (lidar) buoys at selected locations or as forecasting-model-based output from reanalysis products. In situ wind profiles have sparse geospatial coverage and are costly to obtain en masse, whereas satellite-derived 10 m wind speeds have vast coverage at high resolution. In this study, we show the benefit of deploying machine learning techniques, in particular random forest regression (RFR), over conventional methods for accurately estimating offshore wind speed profiles on a high-resolution (0.25°) grid at 6-hourly resolution from 1987 to the present using satellite-derived surface wind speeds from the National Oceanic and Atmospheric Administration (NOAA) National Centers for Environmental Information (NCEI) Blended Seawinds version 2.0 (NBSv2.0) product. We use wind profiles from five publicly available lidar datasets over the northeastern US and Californian coasts to train and validate an RFR model to extrapolate wind speed profiles up to 200 m. A single extrapolation model applicable to the coastal regions of the contiguous US and Hawai`i is developed instead of site-specific models attempted in previous studies. The model outperforms conventional extrapolation methods at the training locations as well as at two additional lidar and six National Offshore Wind (NOW)-23 stations that are independent of the training locations, especially under conditions of high vertical wind shear and at wind turbine hub heights (<span class="inline-formula">∼</span> 100 m). The final model is applied to the NBSv2.0 data from 1987 to the present to create 6-hourly wind speed profiles over the coastal regions of the contiguous US and Hawai`i on a 0.25° grid, which are shown to outperform NOW-23 and European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5) at 100 m using a correlated triple-collocation method over 5 years of matchup data (2015–2019). Gridded maps of wind profiles in the marine boundary layer over US coastal waters will enable the development of a suite of wind energy resources and will help stakeholders in their decision-making related to wind-based renewable energy development.</p> |
|---|---|
| ISSN: | 2366-7443 2366-7451 |