A Machine Learning-Based Correction Method for High-Frequency Surface Wave Radar Current Measurements

Round 1

Reviewer 1 Report

Abstract, Line 14:  high-frequency surface wave radar current measurements

Introduction, Line 35, define ADCP

Material and Methods, Line 64,  in the  at a frequency

line 71, suggest rewording The 10-m surface wind data.  The  standardized  winds at 10 metres were obtained from .....

line116, Define EOF

RESULTS, Line 128, replace tortuous with complex

Figure 2, 3, 4,5 and 6  Label all axis.

Figure 2, line 140, Lmaj and Lmin  Lmaj and Lmin

Figure 6 replace ^"*"  with "_*"

Table 1 and Table 2  - add units. ie RMSE is in m/s

CONCLUSSIONS Line 252-262.  This paragraph should be deleted or moved to the introduction as none of the points raised are mentioned in the body of the work.  The paragraph describes why this is why the work is being undertaken. 

 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

In this manuscript, the authors applied LSTM model along with wind and tide inputs for improving the current estimation results from HF radar. Test using field data shows the proposed model is effective compared with model results. I suggest the authors consider the following problems:

 

1.     The introduction needs improvement: expand and focus more on literature of machine learning for HF radar applications (tide, target…); add a paragraph describing the structure of the manuscript.

2.     Line 59, how can including physical factors improve training efficiency?

3.     Line 30, grammar is incorrect.

4.     Line 158, “was” should be “were”.

5.     Line 174, you attribute the errors in area C to radar system bias, please be more specific.

6.     Comparison with model currents is relatively weak.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

My comments have been addressed, just one suggestion:

1. Reference [10] is a conference paper, it is better to replace it with its journal version which is published in IEEE JSTARS (2021) by the same authors.

Author Response

Many thanks for pointing out this issue, we have revised it in the revised manuscript.

10.  Huang, W.; Yang, Z.; Chen, X. Wave Height Estimation From X-Band Nautical Radar Images Using Temporal Convolutional Network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2021, 14, 11395-11405, doi:https://doi.org/10.1109/JSTARS.2021.3124969.