09 Nov 2022
 | 09 Nov 2022
Status: a revised version of this preprint is currently under review for the journal WES.

Vertical extrapolation of ASCAT ocean surface winds using machine learning techniques

Daniel Hatfield, Charlotte Bay Hasager, and Ioanna Karagali

Abstract. The increasing demand for wind energy offshore requires more hub-height relevant wind information while larger wind turbine sizes require measurements at greater heights. In situ measurements are harder to acquire at higher atmospheric levels; meanwhile the emergence of machine-learning applications has led to several studies demonstrating the improvement in accuracy for vertical wind extrapolation over conventional power-law and logarithmic profile methods. Satellite wind retrievals supply multiple daily wind observations offshore, however only at 10 m height. The goal of this study is to develop and validate novel machine-learning methods using satellite wind observations and near-surface atmospheric measurements to extrapolate wind speeds to higher heights. A machine-learning model is trained on 12 years of collocated offshore wind measurements from a meteorological mast (FINO3) and space-bourne wind observations from the Advanced Scatterometer (ASCAT). The model is extended vertically to predict the FINO3 vertical wind profile. Horizontally, it is validated against the NORA3 meso-scale model reanalysis data. In both cases the model slightly over-predicts the wind speed with differences of 0.25 and 0.40 m s-1 respectively. An important feature in the model training process is the air-sea temperature difference, thus satellite sea surface temperature observations were included in the horizontal extension of the model, resulting in 0.20 m s-1 differences with NORA3. A limiting factor when training machine-learning models with satellite observations is the small finite number of daily samples at discrete times; this can skew the training process to higher/lower wind speed predictions depending on the average wind speed at the satellite observational times. Nonetheless, results shown in this study demonstrate the applicability of using machine learning techniques to extrapolate long-term satellite wind observations when enough samples are available.

Daniel Hatfield et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on wes-2022-101', Anonymous Referee #1, 14 Dec 2022
  • RC2: 'Comment on wes-2022-101', Anonymous Referee #2, 03 Jan 2023

Daniel Hatfield et al.

Daniel Hatfield et al.


Total article views: 420 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
298 105 17 420 9 5
  • HTML: 298
  • PDF: 105
  • XML: 17
  • Total: 420
  • BibTeX: 9
  • EndNote: 5
Views and downloads (calculated since 09 Nov 2022)
Cumulative views and downloads (calculated since 09 Nov 2022)

Viewed (geographical distribution)

Total article views: 404 (including HTML, PDF, and XML) Thereof 404 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 25 Mar 2023
Short summary
Wind observations at heights relevant for the operation of modern offshore wind farms, i.e. 100 m and more, are required to optimize their positioning and layout. Satellite wind retrievals provide observations of the wind field over large spatial areas and extensive time periods yet their temporal resolution is limited and are only representative at the 10 m height. Machine-learning models are applied to lift these satellite winds to higher heights, directly relevant for wind energy purposes.