Study of the Cone-Shaped Drogue for a Deep-Towed Multi-Channel Seismic Survey System Based on Data-Driven Simulations

Round 1

Reviewer 1 Report

Broad comments. The authors have made a concise overview of the topic and a brief reference to existing literature. They have indicated the main task of the paper among its motivation. Finally, they have pointed out the key message and the potential benefits of their work. As a general drawback, I could say that there is no reference to similar approaches (e.g. [1],[2]) where massless particle/fluid methods and error estimation and accuracy of machine learning methodologies have been performed on real datasets in different systems.

1. Spandonidis, Christos C., and Kostas J. Spyrou. "Coupled vessel-dry-granular-cargo roll dynamics in regular beam seas." Ocean Engineering 120 (2016): 238-245.
2. Theodoropoulos, P.; Spandonidis, C.C.; Themelis, N.; Giordamlis, C.; Fassois, S. Evaluation of Different Deep-Learning Models for the Prediction of a Ship’s Propulsion Power. J. Mar. Sci. Eng. 2021, 9, 116. https://doi.org/10.3390/jmse9020116

Specific comments. In general, the text is very well structured and has clearly defined topics. The abstract is a very good guide for what follows. More or less all fundamental theory details that are needed are discussed and concluding remarks are sufficient. Some comments for improvement:

1. It would be beneficial to clarify the reasoning behind the selection of the target feature used. Did authors examine methodology validity and/or accuracy for different target features?
2. Did authors test different models? LSTM RNN or 1D CNN could be a good fit for the problem under discussion.
3. In general, authors could consider adding the citation after reference of authors name (e.g. Papas et al [1], instead of Papas et al ……. [1])
4. It is advisable to remove the work infeasible in line 47.
5. Authors are encouraged to provide a brief description of the MPS method, even though is the default method of the software used. This way the reader would be better informed about the analysis procedure.
6. In line 247, the authors could better describe how the 10% is derived.
7. Similarly, the procedure for the adjustment of the motion constraint equation should be better described (line 252).
8. Authors are encouraged to justify the selection of the number of layers for their models.
9. The number of inputs and outputs referred to in lines 319-323 is not very clear. Authors should better describe it.
10. In addition, the selection of Tanh over ReLu that is mostly used in a similar approach should be provided.
11. It would beneficial if the authors could provide a graph that presents the 2 different time series (predicted polynomial against predicted neural).
12. Besides authors could consider adding scatterplots (predicted vs real data) and compare the R-squared for each case, since direct comparison of the time series makes it very difficult to be followed.
13. Authors could consider enhancing the final section (summary) such that it not only includes a summary of the work (that has already been given in the abstract) but also include a critical review of the applicability o the method and its limitations.

Author Response

Thank you for your professional comments and suggestion, and we are excited to know you are interested in our research. We read your comments carefully, and all of them are answered in the attachement.

Author Response File: Author Response.pdf

Reviewer 2 Report

In the article, the authors present a complete reduction procedure of the hydrodynamic behaviour of cone-shaped drogue. Reduction is based on a simplified Morison hydrodynamic force model. Open coefficients are determined with the fitting procedure. Data set is prepared as a mixture of experimental data and data obtained via numerical simulations.

Results show very good agreement and verify the proposed reduced hydrodynamic model for the simplified calculations of cone-shaped drogue dynamics. The mixture of experiments and numerical simulations support the reduced model in a wide and most correct way.

I would recommend the article to be accepted in the present form with minor text corrections. I would recommend authors to have a thorough text and language article edit.

Author Response

Thank you for your recognition. This manuscript was polished by the Elsevier Language Editing Service, and we checked every modification carefully. Thank you very much. The Language Editing Certification is attached. Thanks again.

Author Response File: Author Response.pdf