Dear authors:

Thank you for submitting reply in the Interactive Discussion, the authors have made the manuscript more consistent with the referee's arguments. In particular I would still suggest clarifying the definition and discussion of the “authors cannot claim HIDRA is better than NEMO because they only compared with results from only one NEMO configuration ” (see comments on original submission by reviewer 2).

In addition, please attention again to the Editorial version 1.2:
https://www.geosci-model-dev.net/12/2215/2019/ This highlights some requirements of papers published in GMD, which is also available on the GMD website in the ‘Manuscript Types’ section:
http://www.geoscientific-model-development.net/submission/manuscript_types.html
It is important to make sure your paper meets all the requirements above.

My reason for returning the manuscript to you at this stage is to allow you to make some minor revise the manuscript in response to the comments of both referees and in response to my own comments above.

Best regards,
Xiaomeng Huang
Handling Topical Editor

Dear authors:

I am pleased to inform you that this manuscript can be published with some minor revisions according to the two referees’ comments.

Specifically, The authors’ response to anonymous referee#1, Comment 2:” The authors declare “Extending the historical horizon beyond 24 hours did not significantly affect the prediction accuracy”. Please give a concise description of how to find the trade-off between the model forecast accuracy and the computing resource.”

In addition, the authors decided to set Tmin = 23, however, the value of Tmin in the new version5 manuscript is still 24. Could you be more specific on how to find the trade-off between the model forecast accuracy and the computing resource? This is relevant for the reader to understand your paper.

Sincerely,
Xiaomeng Huang
Handling Topical Editor

Dear authors:

You thoroughly addressed all my comments. This paper is an important contribution in extending the machine learning to ocean modelling. I believe that this paper will be of great interest to the community. Thank you again for submitting your work to GMD.

Sincerely,
Xiaomeng Huang
Handling Topical Editor