Storm Damage and Planting Success Assessment in Pinus pinaster Aiton Stands Using Mask R-CNN

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This study used deep learning for tree detection in Pinus pinaster stands. The topic is interesting. The designed method is applied for the detection of fallen trees and detecting trees in a newly established plantation after wildfire, which has certain practical application value. Latest references are cited and discussed. The presented information in the introduction is relatively new, which could reflect the latest progress in this area. Some modifications are required. 

1. The materials and methods section is relatively har to read. Please use sub-titles to make this part more clear and easy to follow.
2. It is good that a large quantity of images were captured for analysis and modeling. Since deep learning is used, the preperation and definition of training, validation and testing dataset should be clearly provided. In the current version, this information was missing.
3. From Line 216-223, 'object detection' was mentioned. However, MaskRCNN was a famous instance segmentation model. Please kindly correct the usage of the terminology in deep learning area.
4. What is the purpose of tree detection? Is it just for calculating the quantity of tree? If so, why are relatively complex instance segmentation methods selected? As a fact, object detection models, which could assign a bounding box for each target, could also handle the tree counting task in this study. For example, YOLO-detection model could also realize tree detection. In addition, YOLO models operate more efficiently than MaskRCNN and require less computing resources. Please kindly discuss why MaskRCNN is necessary in this study.
5. Tables should be modified. Please avoid using abbreviations. Or please provide the coresponding full name of all those symbols and abbreviations. Moreover, the term 'Threshold' shold be expressed more clearly, what kind of Threshold was applied here? 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Dear Authors,

I had the chance to read your manuscript. You find some comments and suggestions attached.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

Attached is the review. 

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Thanks. All my concerns have been addressed.