Review History


All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.

Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.

View examples of open peer review.

Summary

  • The initial submission of this article was received on June 3rd, 2022 and was peer-reviewed by 3 reviewers and the Academic Editor.
  • The Academic Editor made their initial decision on August 5th, 2022.
  • The first revision was submitted on September 15th, 2022 and was reviewed by 1 reviewer and the Academic Editor.
  • The article was Accepted by the Academic Editor on September 20th, 2022.

Version 0.2 (accepted)

· Sep 20, 2022 · Academic Editor

Accept

I congratulate the authors for the effort put into this paper! The manuscript is significantly improved; therefore, I recommend accepting it in its current form!

[# PeerJ Staff Note - this decision was reviewed and approved by Richard Schuster, a PeerJ Section Editor covering this Section #]

Reviewer 1 ·

Basic reporting

no comment

Experimental design

no comment

Validity of the findings

no comment

Version 0.1 (original submission)

· Aug 5, 2022 · Academic Editor

Minor Revisions

Overall, the discussion part is weak. The Discussion should summarize the manuscript's main finding(s) in the context of the broader scientific literature and address any study limitations or results that conflict with other published work.

[# PeerJ Staff Note: Please ensure that all review and editorial comments are addressed in a response letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. #]

Reviewer 1 ·

Basic reporting

The text is written clearly. The authors say what they want to do.

Experimental design

The image are collected from the DJI drone. It was collected at different times and dates and this should be fine.

Validity of the findings

I think the findings are plausible and make sense.

Additional comments

I think the paper is fine. I would like to suggest to the authors if I may.
1. Please provide a reason why do you decide to use an image size of 128 x 128 pixels?
2. The author used binary cross-entropy as an objective function. I suggest showing the equation and giving a few details.
3. I suggest that the authors should provide the modified U-net architecture image. it will help the reader understand the U-net architecture.

Reviewer 2 ·

Basic reporting

In this article, the authors proposed an approach for deforestation monitoring by applying a CNN-based segmentation model to accurately classify the canopy cover of Portulacaria afra.

The training datasets are acquired through the UAV imaging platform. Authors are applying a cutting-edge approach to solving a real challenge. However, The article must be written in unclear and ambiguous English and must be written in a form that can attract readers.

Requesting the authors to review the article properly in terms of clear understandable writing.

Experimental design

The experimental set-up design and its analysis are found inadequate throughout the article. Such as,

- Should provide sample training images.
- The reason behind using the Unet model
- Choosing 100 epochs, probably explain the training vs. loss-rate curve.
- Validations results are also important to explain the experimental setup.
- Which type of hyperparameters were tuned and why tuned?
- Proper analysis of segmentation results by applying TP, TN, FP, FN, and accuracy.
- What is the technical shortcoming in the dataset since acquired through UAV?
- The output results need to upload along with the dataset.

Additionally, UAV capturing and its applications are very dependent on image resolution and lighting conditions after eliminating noise. Authors should provide a rigorous justification of how they overcome the limitations of UAVs such as windy, noisy, and bad weather (challenging) conditions.

Validity of the findings

Many works have already been done using the machine learning approach in deforestation. In the article, the authors should provide varieties of dataset images to show how challenging it is to make the proposed approach robust. Also, the claims need to be validated.

Only an F1 score is not enough to justify it.

·

Basic reporting

No Comment.

Experimental design

No Comment.

Validity of the findings

No Comment.

Additional comments

None.

All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.