Dual-Frequency Radar Retrievals of Snowfall Using Random Forest

Round 1

Reviewer 1 Report

Dear authors,

I thank you for the manuscript provided for the peer-review consideration. It was a pleasure to read it -- from the very "to the point" introduction through clearly presented methods and datasets and solid results and their discussion. I would like to see more papers like yours submitted in scientific journals. I wish you good luck with other projects.

Author Response

Dear reviewer:

Thank you for your affirmation. Your opinion is a great encouragement to us. We will continue our research in this area and get more research results. 

Kind regards,

Authors

Reviewer 2 Report

The submitted paper by Tiantian et al. titled: "Dual-frequency radar retrievals of snowfall using Random Forest", deals with retrieving microphysical parameters of snowfall. The authors investigate if the random forest technique can be used to get snowfall microphysical parameters, such as mass-weighted diameter, snowfall rate, ice water content and particle size distribution parameters. During the current research, 21 snowfall events are elected to be analyzed. The results reveal that the random forest method could provide important results to retrieve microphysical parameters of snowfall. The sources of the data which are used, and their characteristics are also referred. The subject is interesting as the use of satellite snowfall data for hydrological research and numerical weather prediction models is under-progress research. Unfortunately, the main concern for the publication of this research is the structure of the text. The document needs to be rewritten in a lot of parts such as the chapter “Data and instruments”.

My recommendation is major revisions.

General Comments

-Change keywords. Avoid using the same words that already exist in the title.

-The manuscript needs to be improved. Please correct the syntaxis. 

-Table1. Correct the date (yy/mm/dd).

-Provide more information about the study area.

-Conclusions should provide only the take-home message.

-Which software is used in the current work?

Author Response

Dear reviewer:

Thank you for your comments on our manuscript entitled "Dual-frequency radar retrievals of snowfall using Random Forest". Those comments are very helpful for revising and improving our paper, as well as the important guiding significance to other research. We have studied the comments carefully and made corrections which we hope meet with approval. The main corrections are in the manuscript and the responses to the reviewers’ comments are as follows.

1. Change keywords. Avoid using the same words that already exist in the title.

Response. Keywords have been changed as: D3R; disdrometer; microphysical parameters; look-up table method; random forest method.

2. The manuscript needs to be improved. Please correct the syntaxis.

Response. The manuscript has been improved from the beginning to the end.

3. Table1. Correct the date (yy/mm/dd).

Response. The date has been corrected.

4. Provide more information about the study area.

Response. Information has been added from Line104 to Line108.

5. Conclusions should provide only the take-home message.

Response. The conclusion has been revised and related to the present work.

6. Which software is used in the current work?

Response. We used Scikit-Learn in Python to train the model, which is a free machine learning library. It is specified in Line 205-206.

Once again, thank you very much for your constructive comments and suggestions which would help us both in English and in depth to improve the quality of the paper.

Reviewer 3 Report

Review report #01

Manuscript ID: remotesensing-1719790

Manuscript title: Dual-frequency radar retrievals of snowfall using Random Forest

Authors: Tiantian Yu 1, V. Chandrasekar 2, Hui Xiao 3, Ling Yang 1, *, Li Luo 4, and Xiang Li

Summary:

            In this manuscript, the authors tried to validate the Random Forest (RF) method to evaluate the snowfall parameters using D3R and Parsivel disdrometer measurements over South Korea. The authors reported that the RF method can better estimate the snowfall parameters than the traditional lookup table method. In most instances, the manuscript is clearly written. However, there are some instances where authors need to amend/provide more explicit information. Here are my few minor suggestions before accepting the manuscript in the remote sensing journal.

Minor comments:

1. Page 4, table 1. Please mention the time of each snowfall day in Table 1.
2. Page 5, lines # 170-171: The sentence is not clear; please check and rewrite it.
3. Page 6, lines # 210-213: Please check the sequence of mentioning the subplot figures.
4. Page 7, lines # 231-233: The sentence is unclear.
5. Page 8, section 3.2: More detailed information regarding Random Forest (RF) method is recommended.
6. Page 11, line # 217: Please check the typo error in “if RF models,….”
7. Page 13, lines 316-319: The sentence is unclear; please rewrite it.
8. Page 13, section 5. The last paragraph of the conclusion section (lines # 330-336) seems like an introduction. It is not strictly related to the conclusions of the present work.

Author Response

We thank the reviewer for valuable comments and we have studied these carefully and made corrections accordingly. The itemized response is below.

1. The time of each snowfall day has been mentioned.
2. The sentence has been rewritten.
3.  Sorry for miswriting. It has been revised.
4. The sentence has been revised.
5. More detailed information regarding Random Forest (RF) has been added.
6. Sorry for the error, it is "of".
7. The sentence has been rewritten.
8. This paragraph has been deleted.

Special thanks to you and your good comments.

Round 2

Reviewer 2 Report

The manuscript has been revised. I suggest publication

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.