Study of the Performance of Deep Learning Methods Used to Predict Tidal Current Movement
, Xiaoyong Wang 1, He Wu 1,*, Xuefeng Zhang 2, Yizhou Fang 1, Lianxin Zhang 3 and Haifeng Wang 1
Round 1
Reviewer 1 Report
Dear authors,
Your manuscript “Study on the Performance of Deep Learning Methods used to Predict Tidal Current Movement” is very interesting and relevant. I have the following comments
It would be important to highlight the scientific novelty and research contribution of your study, contrasting it with previous studies as mentioned in your introduction. What are the most significant improvements that your research provide? This can be indicated in the last paragraphs of your introduction. Indicating the hypothesis and research activities will be also relevant for this section.
The data applied to your research is from 30 May to 9 July 2021. In section 3.2.1. one location is mentioned but in section 3.1.1. two locations are mentioned. Was the data from one or two locations?
Considering that tidal energy is seasonal and has high variability is the length of the dataset applied sufficient to validate the model. What is the level of uncertainty introduced in the model validation from limited dataset (38 days and one location). Is it possible that higher variability may generate diverse results?
Which is the error generated by the numerical model, as indicated in Figure 7. What is the indicator for goodness of fit that can be applied for these results. I believe the figures are a good way of showing goodness of fit but having an objective indicator, that may be compared with other models, may be important.
Is it possible to compare the deviations of the numerical models for tidal velocity with results generated by previous research, to showcase the improvement and research contribution provided by this research?
It will be important to connect the results in the manuscript with the hypothesis and research contribution. Was the hypothesis proven or disproven by the results generated in your study? It will be important to validate this.
The conclusion should be expanded, to include additional results that showcase the novelty and scientific contribution of the research. Adding the limitations of the study and future research will be also important.
Author Response
Please see the attachment
Author Response File: 
Author Response.pdf
Reviewer 2 Report
See attached file
Comments for author File: 
Comments.docx
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 3 Report
The paper requires major revisions:
1-What is abbreviation of attention-resnet neural network (ATT-RES) in the paper?? The correct version pf attention-resnet neural network (ATT-RES) is attention-resnet neural network (AR-ANN).
2-Quantitative performance of multilayer perceptron(MLP), long-short term memory(LSTM) and attention-resnet artificial neural network(AR-ANN) should be mentioned in the abstract.
3-Why did authors utilized such machine learning models to predict tidal current movement?
4-Literature review should be enhanced in terms of quality and quantity. Some applications of machine learning models into ocean engineering can be furnished and maybe useful:
-Estimation of Scour Propagation Rates around Pipelines While Considering Simultaneous Effects of Waves and Currents Conditions
-Scour Propagation Rates around Offshore Pipelines Exposed to Currents by Applying Data-Driven Models
5-General descriptions of these machine learning methods should be mentioned.
6-Setting parameters of machine learning models should be justified and clarified?
7-The results of the present study should be comprehensively compared with literature.
8-Conclusion section was rather poorly written.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Dear authors
Most of the review comments were addressed in this version of the manuscript. Thank you for the revised manuscript and your letter of response
Reviewer 2 Report
Despite the authors' responses are not plainly convincing, I appreciated the effort to improve the quality of the paper.
Reviewer 3 Report
Accept as is
