Dear authors,

Three reviewers have now provided very helpful and thorough comments on your manuscript.

Reviewers 1 & 2 have concerns about the validation and the prediction steps which will need to be addressed.

I think also that the use of R2 could be confusing. The problem is that R2 can refer both to the coefficient of determination of a linear regression between predicted and observed (i.e., the square of the Pearson correlation coefficient) as well as to the amount of variance explained by the model. The first evaluates how close predicted and observed are to a fitted straight line, while the second evaluates how close they are to the 1:1 line. It is the latter that we are after in statistical validation, and this is properly assessed using the (Nash-Sutcliffe) Model Efficiency Coefficient (MEC). In the manuscript, the way you compute the R² seems to be wrong. You are missing 1 minus the ratio.

Best regards

I am pleased to inform you that your paper has been accepted for publication. Reviewer comments are appended to the end of this letter. Now that your manuscript has been accepted for publication it will proceed to copy-editing and production.
Thank you for submitting your work to Soil. We hope you consider us again for future submissions.

Dear authors,

Based on the report of the Topical Editor, I am happy to inform you that your paper is now accepted. However, there are still some minor corrections needed (see reviewers report), please carefully check the manuscript before submitting your final version to Coperniucs.

Kind regards,

Kristof Van Oost