Next Article in Journal
Genome-Wide Association Analysis and Candidate Gene Prediction of Wheat Grain Copper Concentration
Previous Article in Journal
SmartPod: An Automated Framework for High-Precision Soybean Pod Counting in Field Phenotyping
 
 
Article
Peer-Review Record

Predicting Sugarcane Yield Through Temporal Analysis of Satellite Imagery During the Growth Phase

Agronomy 2025, 15(4), 793; https://doi.org/10.3390/agronomy15040793
by Julio Cezar Souza Vasconcelos 1, Caio Simplicio Arantes 1, Eduardo Antonio Speranza 2, João Francisco Gonçalves Antunes 2, Luiz Antonio Falaguasta Barbosa 2 and Geraldo Magela de Almeida Cançado 2,*
Reviewer 1: Anonymous
Reviewer 2:
Reviewer 3: Anonymous
Agronomy 2025, 15(4), 793; https://doi.org/10.3390/agronomy15040793
Submission received: 11 February 2025 / Revised: 12 March 2025 / Accepted: 18 March 2025 / Published: 24 March 2025
(This article belongs to the Section Precision and Digital Agriculture)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This is an interesting work about sugarcane yield estimation using multi-temporal satellite imagery. The estimation idea is clearly stated, and the experimental results show the pleasing estimation performance. This paper needs to be improved further before it can be accepted for publication, especially providing more details. My comments are as follows:

1) The English could be improved to more clearly express the research.

2) The research situation is not well introduced. More related studies (especally, the references published after 2020) need to be introduced. The drawbacks of these studies need to be conclude more clearly and precisely.

3) Please Highlighting the innovations of this work at the end of Section 1.

4) Figure 1. It is better to use a map to show the precisely geographic locations of the study areas, which is helpful for readers to reproduce your work. Similarly, please using a map (in the manuscript, not in the Supplementary file) to show the precisely geographic locations of the Commercial Area.

5) At present, Section 2 are too lengthy, because the authors have put all the contents about the datasets and methodology together. So, I suggest to divide them as the Study Area and Dataset Section and the Methodology Section.

6) The datasets used for training and testing are not clearly stated in Section 2. From the experimental results, the model is tested in both the Field Data and the Commercial Data. But the statement in Section 2.2 may mislead the readers that only the Commercial Data is used for testing. Similarly, from the Supplementary file, I can see that, for the Commercial Data , there are some "training files". But, in the paper, the authors only mentioned that, the Field Data is used for model training, which makes me confusing.

7) It was mentioned that the sattelite images using in this study have eight bands. Which eight bands (the wavelength of each band)?

8) Only the precipitation data are used when considering the influence of weather. Is it reasonable? or, can we get better results if we consider the temperature? This can be discussed in the Conclusion Section.

9) A mistake in Figure 3. "The shaded regions .... which were incorporated into predictive models to estimate sugarcane productivity". But, in fact, the "pink areas" are also used for estimation.

10) Only list those assessment indicators is not clearly enough for readers to judge the performance of the model. I suggest the authors to show some productivity data (the actual ones and the estimated ones) of some typical field plots in the tables.

Comments on the Quality of English Language

The English could be improved to more clearly express the research.

Author Response

see attached file

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The article has strong potential, however some sections should be improved.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

The English quality is good, but it could be improved to more clearly express the research.

Author Response

see attached file

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

Dear authors,

The research shows an acceptable monitoring and explanation of the estimation of sugarcane productivity. They consider times of the year, the region, growing season and environmental variants. There is access to the database, and they consider the recommended GNDVI or satellite greenness indices to evaluate their models and prediction during the growth phase. The authors use Heteroscedatic GA, RF and NN machine learning techniques to improve productivity with respect to R2, as well as the estimation parameters.

In the cultivation region of this sugarcane, expanding AI techniques with satellite help favors prediction model techniques to optimize factors in precision agriculture as well as product quality for the consumer.

The following reference is recommended:

https://doi.org/10.1016/j.compag.2022.107024

 

 

Author Response

see attached file

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

I have no more questions.

Author Response

answers in the attached file

Reviewer 2 Report

Comments and Suggestions for Authors

The authors have made some improvements to the manuscript since the first submission; however, not all comments from the first round of review have been addressed.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

The English quality is good, but there is room for improvement.

Author Response

answers in the attached file

Author Response File: Author Response.pdf

Round 3

Reviewer 2 Report

Comments and Suggestions for Authors

The authors have addressed all the comments.

I have no more comments.

Comments on the Quality of English Language

The English could be improved to more clearly express the research

Back to TopTop