Preprints
https://doi.org/10.5194/amt-2021-200
https://doi.org/10.5194/amt-2021-200

  26 Jul 2021

26 Jul 2021

Review status: a revised version of this preprint was accepted for the journal AMT.

Support vector machine tropical wind speed retrieval in the presence of rain for Ku-band wind scatterometry

Xingou Xu1 and Ad Stoffelen2 Xingou Xu and Ad Stoffelen
  • 1The CAS Key Laboratory of Microwave Remote Sensing, National Space Science Center, Chinese Academy of Sciences, Beijing, 100190, China
  • 2Royal Netherlands Meteorological Institute, De Bilt, 3730 AE, The Netherlands

Abstract. Wind retrieval parameters, i.e., quality indicators and the 2DVAR analysis speeds, are explored with the aim to improve wind speed retrieval during rain for tropical regions. We apply the well-researched support vector machine (SVM) method in machine learning (ML) to solve this complex problem in a data-orientated regression. To guarantee the effectiveness of SVM, the inputs are extensively analysed to evaluate their appropriateness for this problem, before the results are produced. Subsequently, triple collocation shows that the similarity of the resolved Ku-band (OSCAT-2) wind speed in rain is better than the 2DVAR speed, with respect to the collocated C-band (ASCAT) speed, which is much less affected by rain. The comparisons between distributions and differences between data of rain-contaminated winds, corrected winds and good quality C-band winds, illustrate that the rain-distorted wind distributions become more nominal with SVM, hence eliminating rain-induced biases and error variance. Further confirmation is obtained from a case with synchronous Himawari-8 observation indicating rain (clouds) in the scene. Furthermore, the determination of simultaneous rain rate is attempted to retrieve both wind and rain. Although, additional observations or higher resolution may be required to better assess the accuracy of the wind and rain retrievals, the Machine Learning (ML) results demonstrate benefits of such methodology in geophysical retrieval and nowcasting applications.

Xingou Xu and Ad Stoffelen

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on amt-2021-200', Anonymous Referee #1, 31 Jul 2021
    • AC1: 'Reply on RC1', Xingou Xu, 27 Aug 2021
  • RC2: 'Comment on amt-2021-200', Anonymous Referee #2, 17 Aug 2021
    • AC2: 'Reply on RC2', Xingou Xu, 27 Aug 2021
    • AC3: 'Reply on RC2', Xingou Xu, 27 Aug 2021

Xingou Xu and Ad Stoffelen

Xingou Xu and Ad Stoffelen

Viewed

Total article views: 504 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
407 82 15 504 2 2
  • HTML: 407
  • PDF: 82
  • XML: 15
  • Total: 504
  • BibTeX: 2
  • EndNote: 2
Views and downloads (calculated since 26 Jul 2021)
Cumulative views and downloads (calculated since 26 Jul 2021)

Viewed (geographical distribution)

Total article views: 448 (including HTML, PDF, and XML) Thereof 448 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 21 Oct 2021
Download
Short summary
The Support Vector Machine can effectively represent the increasing effect of rain in affecting wind speeds. This research provides correction of deviations that are skew to Gaussian-like features caused by rain in Ku-band scatterometer wind. It demonstrates the effectiveness of a Machine Learning method when used based on elaborated analysis of the model establishment and result validation procedures. The corrected winds provide information previously lacking, while vital for nowcasting.