Separation of convective and stratiform precipitation using polarimetric radar data with a support vector machine method

Wang, Yadong; Tang, Lin; Chang, Pao-Liang; Tang, Yu-Shuang

doi:https://doi.org/10.5194/amt-14-185-2021

Articles | Volume 14, issue 1

https://doi.org/10.5194/amt-14-185-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-14-185-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 14, issue 1

Research article

|

12 Jan 2021

Research article |

| 12 Jan 2021

Separation of convective and stratiform precipitation using polarimetric radar data with a support vector machine method

Yadong Wang, Lin Tang, Pao-Liang Chang, and Yu-Shuang Tang

Download

Final revised paper (published on 12 Jan 2021)
Preprint (discussion started on 18 Dec 2019)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'Separation of Convective and Stratiform Precipitation Using Polarimetric Radar Data with A Support Vector Machine Method', Anonymous Referee #2, 02 Jan 2020
- AC1: 'Reply to Reviewer 2', Yadong Wang, 09 Jan 2020
RC2: 'revision of amt-2019-324', Anonymous Referee #3, 26 Apr 2020
- AC2: 'Reply to Referee #3', Yadong Wang, 07 Jun 2020
RC3: 'Review of "Separation of Convective and Stratiform Precipitation Using Polarimetric Radar Data with A Support Vector Machine Method"', Anonymous Referee #4, 11 May 2020
- AC3: 'Reply to Referee #4', Yadong Wang, 07 Jun 2020

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

AR by Yadong Wang on behalf of the Authors (07 Jun 2020) Author's response Manuscript

ED: Referee Nomination & Report Request started (07 Jul 2020) by Saverio Mori

RR by Anonymous Referee #2 (20 Jul 2020)

Suggestions for revision or reasons for rejection

First of all, there have been a number of improvements to the paper with regards to the adding of additional details which significantly helped to improve the paper. But, it also left a number of inconsistencies that need to be removed before publication. First, as I read into the details, I saw in lines 182 through 184 that only one case was used to train the convective portion of the SVM technique… This seems very small.... If this is true, how many cases (not just radar tilts) were used to train the stratiform portion of the SVM technique... This is one of the chief reasons I rated the scientific quality as only fair.... Otherwise, I would've rated it higher.

Also, the overall readability and the English needs to be improved significantly.... The reason is there are statements written that will convey to the reader an opposite meaning than what the authors clearly intended. An example, can be found in line 227.... Where the authors mention that POD, FAR and CSI can't really capture the performance of the SVM technique… If that were true why bother with those statistics… However, I think the authors really meant that these statistics only partially capture the performance and therefore a new performance evaluation statistic should also be considered. The same subject was also mentioned in the conclusion in lines 332 through 335 and should be clarified there as well.....where it significantly caused me to wonder why the stats were even used..... Again, I know the authors didn't intend that meaning..... But the way it is written conveyed that type of meaning.

While I think the authors significantly improved the amount of detail needed for publication and that there is significant scientific merit to the work I just don't think it's ready for publication yet without significant major revisions to improve the readability of the paper. However, I definitely think this paper should be revised because I believe it does carry information that would be useful for the scientific community once the revisions are made. While I know this may be discouraging for the authors, they need to realize that important that they keep moving forward on this paper because persistence will ultimately result in excellence!

Hide

RR by Anonymous Referee #4 (21 Jul 2020)

ED: Reconsider after major revisions (25 Jul 2020) by Saverio Mori

AR by Yadong Wang on behalf of the Authors (04 Sep 2020) Author's response Manuscript

ED: Publish subject to minor revisions (review by editor) (27 Sep 2020) by Saverio Mori

AR by Yadong Wang on behalf of the Authors (06 Oct 2020) Author's response Manuscript

ED: Publish as is (31 Oct 2020) by Saverio Mori

Short summary

The motivation of this work is to develop a precipitation separation approach that can be implemented on those radars with fast scanning schemes. In these schemes, the higher tilt radar data are not available, which poses a challenge for the traditional approaches. This approach uses artificial intelligence, which integrates polarimetric radar variables. The quantitative precipitation estimation will benefit from the output of this algorithm.