Next Article in Journal
Unsupervised Adversarial Domain Adaptation with Error-Correcting Boundaries and Feature Adaption Metric for Remote-Sensing Scene Classification
Previous Article in Journal
Improving Spatial Coverage of Satellite Aerosol Classification Using a Random Forest Model
Previous Article in Special Issue
Improved Prototypical Network Model for Forest Species Classification in Complex Stand
 
 
Article
Peer-Review Record

A New CBAM-P-Net Model for Few-Shot Forest Species Classification Using Airborne Hyperspectral Images

Remote Sens. 2021, 13(7), 1269; https://doi.org/10.3390/rs13071269
by Long Chen 1,2,†, Xiaomin Tian 3,4,†, Guoqi Chai 1,2, Xiaoli Zhang 1,2,* and Erxue Chen 5
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Remote Sens. 2021, 13(7), 1269; https://doi.org/10.3390/rs13071269
Submission received: 16 February 2021 / Revised: 21 March 2021 / Accepted: 24 March 2021 / Published: 26 March 2021
(This article belongs to the Special Issue Remote Sensing of Biodiversity in Tropical Forests)

Round 1

Reviewer 1 Report

In the paper: “A new CBAM-P-Net model for few-shot forest species classification using airborne hyperspectral images authors proposed modification of the prototypical  networks for species classification using airborne hyperspectral images.

I find this manuscript to be a well written and nicely straightforward paper that, with some work, will make a nice contribution to the literature and practice. Proposed method turned out to be effective and can probably be applied to other classification problems.

A few  comments:

  • Introduction section is too long and should be shortened
  • The effectiveness of the method has been confirmed but the word “significantly” used in text are often is exaggerated. Statistical significance was not tested.
  • Its only single case study. It would be good to show the effectiveness of the method with examples of more than one study area
  • the formula for kappa should be corrected

 

Summarizing, I do recommend this work for publication after minor revision in line with the comments.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Dear Authors, 

I have reviewed the paper entitled "A new CBAM-P-Net model for few-shot forest species classification using airborne hyperspectral images". In my opinion the paper is interesting but it needs revision. Please, see the comments below. 

Abstract
In the Abstract I could only suggest to extend the description of method's limitations.

Introduction
What is the reason to introduce the public data and present its properties ? The Authors collected data by their own. 

Line 101. Can you just use spectrometer ? From my experience, these instruments arent so expensive, so I think that the Authors should extend the parapgraph and show why samples are expensive and scarce relatively.  Hyperspectral Cameras are much much more expensive in comparison to the ground samples measurements. 

Lines 113-113 There should be a reference for this sentence. 

In the summary of the Introduction I could suggest to add few sentences about the success limitations of proposed model.

Materials and Methods

2.2.1 In my opinion it could be a good practice to add a Table with all of the technical data of the equipment. I think there should be a comment about the usage of sensors. For instance in the Introduction the whole idea was to process the hyperspectral data and yet, the platform includes f.e. LiDAR. 

Please remember that all of the equipment should have a description about manufacturer. 

Therefore I think that the paper is interesting. The presentation of the results is good and understandable. 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

Dear Authors, 

 

Thank you for addressing all of my comments. 

Back to TopTop