Dear authors,

From your responses and the revised version of the manuscript, I consider that you have addressed the main concerns raised by the reviewers.

In my view, there remain two minor issues to be corrected before the manuscript is acceptable for publication:
1. You use a neural network to describe the relationship between propagation and backscattering variables (section 3.1). Only the RMSE is mentioned in the text, and I strongly recommend to add more information (you have thousands of points and simple networks, so limited risks of overfitting, but such aspects - learning curves for instance - should still be provided to the reader...).
2. Regarding item 5 of Reviewer 2, I would recommend to add in the manuscript (end of new Section 3.5) the reference to figures 9,10 and 11 to justify the value of 0.5 deg for the noise in DP (as was done in the responses).

Best regards,

Alexis Berne

My comments have been properly addressed by the authors, so I am happy to accept this manuscript for publication in AMT!