Accumulated Heating and Chilling Are Important Drivers of Forest Phenology and Productivity in the Algonquin-to-Adirondacks Conservation Corridor of Eastern North America
Round 1
Reviewer 1 Report
Dear Authors,
thank you very much for your interesting manuscript. I like the idea, which fixes to the current challenges, but the manuscript is not so easy to read, first you present a lot of well-known statements, the text is too general.
You need to add much more details, the Introduction should present current solutions, how other researchers solve out the problem, what kind of methods are used, and what results are scored? It can allow you to justify why you use the proposed method.
The input data and details of processing methods are not so clear. Please, add much more details oriented on testing and verification.
You present a lot of results, but it is not so clear what is more/less important.
You need to add much better description of validation of used model and an accuracy assessment. It is very important part of all analyzes.
Discussion is interesting, but in many cases it looks like a state-of-art, please add much more direct comparisons of your own results and outcomes presented in references, trying to highlight an improvement of results by your method. Readers are interested in a progress, so please, try to emphasize which elements of the used method allowed to obtain better results?
You could reduce ~15-20% of the text, and the quality of your ideas could be much better, because there are a lot of words, which can be easily eliminated.
Much more details are presented in the attached manuscript.
Best regards
Reviewer
Comments for author File: 
Comments.pdf
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
Dear authors,
I enjoyed reading your manuscript and I have made only some minor comments.
One major point though is that you randomly split your data, while there are other approaches in the ML literature that take into account spatial autocorrelation in these models (I have provided some relevant references).
I think that you should at least compare the two approaches.
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
Dear Authors,
thank you very much for your revised version, which looks much better, but there are still some comments. In the Methods please describe much more details why did you use 25% of your data set as a validation? It is an important question for many researchers.
Discussion still looks like a state-of-art, so please, more direct comparisons of your more important outcomes with references.
There are some editorial errors, e.g. I suggested some improvements of Figure 1, which is not visible in the manuscript.
More technical comments you can find in the attached manuscript.
Best regards
Reviewer
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 2 Report
Dear authors,
Thank you for addressing all my concerns and I congratulate you for a very nice and well-written manuscript. Figures 1 and 3 were missing from the main text, so during proof-reading, please take care to include them in the text.
Author Response
Dear reviewer,
Thank you for your quick attention and for your complements on our work.
We apologize for the missing figures and have done our best to correct bugs in the draft. We hope that you will be able to see the ways that we incorporated your suggestions for Figure 1 in the new draft.
We appreciate your feedback and are grateful to see our manuscript improve with your suggestions.
Stay safe,
Authors
