Next Article in Journal
Combining Satellite Imagery and a Deep Learning Algorithm to Retrieve the Water Levels of Small Reservoirs
Previous Article in Journal
Your Input Matters—Comparing Real-Valued PolSAR Data Representations for CNN-Based Segmentation
Previous Article in Special Issue
SiameseNet Based Fine-Grained Semantic Change Detection for High Resolution Remote Sensing Images
 
 
Article
Peer-Review Record

Extracting Plastic Greenhouses from Remote Sensing Images with a Novel U-FDS Net

Remote Sens. 2023, 15(24), 5736; https://doi.org/10.3390/rs15245736
by Yan Mo 1,*, Wanting Zhou 1 and Wei Chen 2
Reviewer 1: Anonymous
Reviewer 2:
Reviewer 3: Anonymous
Remote Sens. 2023, 15(24), 5736; https://doi.org/10.3390/rs15245736
Submission received: 17 October 2023 / Revised: 10 December 2023 / Accepted: 11 December 2023 / Published: 15 December 2023
(This article belongs to the Special Issue Multisource Remote Sensing Image Interpretation and Application)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors


Comments for author File: Comments.pdf

Author Response

Please see attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

 

1)The study introduces U-FDS Net, a deep learning network designed for efficient plastic greenhouse extraction form remote sensing images for environmental management and agricultural planning.

 

2)The Research paper provides respectable findings and is well-written, but before it is accepted, it needs to be strengthened in the following ways:

 

3)Author should discuss, How does the U-FDS Net differ from existing methods in extracting plastic greenhouses from remote sensing images.

 

4)Author should elaborate on the novel aspects introduced by the U-FDS Net in comparison to traditional or state-of-the-art approaches.

 

5)The proposed method's comparison in terms of accuracy, precision, and other related techniques in the literature should be covered by the author in the introduction section.

 

6)The author also addresses the dataset's possible limitations and how they might affect the applicability of the suggested methodology.

 

7)The U-FDS Net's computational efficiency, sensitivity to input parameters, and robustness to varying scenarios like seasonal changes are being evaluated through practical experiments.

 

8)The implications of the research's findings on environmental or agricultural monitoring techniques should be covered by the author.

 

9)The author should discuss the use of ground truthing for model validation, as the study's results confirm the model's accuracy.

 

10)The software/tools used for data analysis should be named by the author. The author must explain the features of the satellite data that was used.

 

11)The author should define all abbreviations before using them even if they are well known.

 

12)The author must include logical justifications for the results, limitations, and recommendations for future study on performance enhancements.

 

Comments on the Quality of English Language

Comments on the Quality of English Language

The paper requires careful polishing of its English presentation, addressing grammatical issues,  and addressing typos and poorly written sentences. 

 

Author Response

Please see attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

This paper is considered to be an image extraction paper of plastic greenhouse through U-FDS. It appears to have been studied using a variety of AI techniques, and is open for revision after the following minor review fixes.

 - In your conclusion, please provide a numerical representation of how efficient U-FDS is compared to other AI methods.

Author Response

Please see attachment.

Author Response File: Author Response.pdf

Back to TopTop