A Self-Supervised One-Shot Learning Approach for Seismic Noise Reduction
, Roosevelt de Lima Sardinha 1, Pablo Machado Barros 2, André Bulcão 2, Bruno Vieira Costa 3 and Alexandre Gonçalves Evsukoff 1Round 1
Reviewer 1 Report
Comments and Suggestions for Authorssee attached file
Comments for author File: 
Comments.pdf
see attached file
Author Response
Dear Editor,
Attached, please find the file containing our responses to the corrections and suggestions. Additionally, we have uploaded the revised manuscript as a PDF in the "Manuscript (PDF Version)" section, with all modifications highlighted in red.
Thank you for your consideration.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThe paper presents a new method for denoising Noise2Noise which is applied to the seismograms both synthetic and from the real experiment.
The results are promising, however, the description of the method is very unclear for me. To improve readability of the paper, please consider these suggestions:
1) Please, explain more clearly, what are the parameters theta, which are defined in equations (2) and (3) in case of your examples in chapters 4. And also, which definition of misfit function is used.
2) Fig.1 : Please, give more detailed explanation, what do you mean by „dimensions of independent features“, the figure seems to me not clear. And what is the reason of distribution of grey boxes in 1b? Why they do not cover the whole area of the seismograms?
3) Fig.2 and Fig.3 The Noisy Image and Output Image are the same. I understand, that it is only block diagram, but it is confusing.
4) Fig.8 In case of FCN3 the PSNR decreases at Epoch 1750, which is a little strange in my opinion. Please, make some comment of this.
The method could be very useful in automatic recognition of phases of seismograms, however it should be better described.
Author Response
Dear Editor,
Attached, please find the file containing our responses to the corrections and suggestions. Additionally, we have uploaded the revised manuscript as a PDF in the "Manuscript (PDF Version)" section, with all modifications highlighted in red.
Thank you for your consideration.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
Comments and Suggestions for AuthorsThe manuscript has improved after the revision. I found reactions to all my comments.
Author Response
Dear Reviewer,
Thank you for your feedback. We have provided a new version of the article with images of higher resolution to enhance the overall quality. Additionally, we have added a paragraph at the end of the article comparing our work with the state of the art.
