Dear Dr. Wang,

thank you for submitting a revised version of your manuscript and a response to the two detailed reviewer reports. The reviewers had expressed several concerns regarding the reproducibility and representation of your study and you have addressed most of these concerns in the revised version.

However, I would like to invite you to also address the executive editor's comment regarding data source and code archiving before I can recommend publication. Specifically, see exec. editor comment:

"...the datasets used to conduct the evaluation experiments presented must be cited from the code and data availability section with enough precision to allow a reader to reproduce the work in the manuscript."

" Github is an excellent development platform, but it lacks the features required of an archive. GitHub themselves tell authors to use Zenodo for this purpose. The authors should follow the procedure detailed there to archive the exact version of the software used to create the results presented: https://guides.github.com/activities/citable-code/. The resulting Zenodo repositories present the bibliography entries to use"

Please refer to the following documents containing
- further details on code and data availability requirements: https://www.geoscientific-model-development.net/about/code_and_data_policy.html
and its motivation:
https://doi.org/10.5194/gmd-12-2215-2019

Best, Sandra Arndt