Deep Learning Convolutional Neural Network Applying for the Arctic Acoustic Tomography Current Inversion Accuracy Improvement
, Zichen Wang 1, Can Lu 1, Long Fan 2, Zhongzheng Li 2 and Jiaxin Zhou 2Round 1
Reviewer 1 Report
The manuscript uses a CNN based approach for Arctic Acoustic Tomography Current Inversion Accuracy Improvement. The authors provide a detailed explanation of the method.
Author Response
Dear Editors and Reviewers,
Firstly, thank you for your work on this manuscript. I believe everything will go well in the revised version.
"Please see the attachment."
Kind regards.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
This article presents a deep learning convolutional neural network applying for the arctic acoustic tomography current inversion accuracy improvement.
In the methods based on deep learning, the teaching and validation set is an important element. The effectiveness of forecasting and the thesis formulated largely depends on the selection of criteria, as well as the quantity, scope and quality of data. Therefore, the universality of the algorithm has some limitations. I propose to describe in more detail on what basis and what is the reason for the selection of input data for the given research problem.
The authors could also refer to other algorithms in more detail, indicating why the proposed method should be better and more effective.
The article requires minor linguistic corrections.
Author Response
Dear Editors and Reviewers,
Firstly, thank you for your work on this manuscript. I believe everything will go well in the revised version.
"Please see the attachment."
Kind regards.
Author Response File: Author Response.pdf
