Summer Maize Growth Estimation Based on Near-Surface Multi-Source Data
Round 1
Reviewer 1 Report
The objective of this study is to monitor maize LAI and SPA more quickly and more accurately, and to develop an analysis model that has better generalization capabilities. UAV multispectral data, near-ground hyperspectral data, and environmental data were collected. This study then proposes a novel method of monitoring LAI and SPAD in maize 516 based on multi-source data and traditional regression models.
Some concerns were:
line 16 : The abbreviation of leaf area index (LAI) should be mentioned here
Line 20: the complete name of the UAV should be mentioned here
line 79: should not begin a sentence with ""And"
Fig.1: More information is needed in the legend about the sampling area.
Author Response
Dear Editor,
Thank you for allowing a revision of our manuscript, with an opportunity to address the reviewer’s comments. We have studied the reviewer’s comments carefully and have made revisions marked with the revised format in the manuscript.
We are uploading (a) our point-by-point response to the comments (below) (response to reviewers), (b) an updated manuscript with blue highlighting indicating changes (Word document).
We would like to express our great appreciation to you and the reviewers for your comments on our manuscript. We treasure the opportunity and wish that you and the reviewers would acknowledge the revised manuscript. Please inform us if you think the manuscript needs to modify again. We can revise the manuscript till you and the reviewers are satisfied. We are looking forward to hearing from you soon.
Best regards,
Author Response File: 
Author Response.docx
Reviewer 2 Report
Summary, and overall contribution:
Rapid and accurate crop chlorophyll content estimation and leaf area index are crucial for guiding field management and improving crop yields.
this paper proposed a maize leaf area index (LAI) and soil plant analytical development (SPAD) monitoring method based on multi-source data using machine learning and traditional regression models.
Minor comments:
- The abstract is too long (432 words) consider shortening it to like (250 words) or less.
- It could be more insightful to include a Neural network method (eg MLP) in comparison to the other classical ML models.
Author Response
Dear Editor,
Thank you for allowing a revision of our manuscript, with an opportunity to address the reviewer’s comments. We have studied the reviewer’s comments carefully and have made revisions marked with the revised format in the manuscript.
We are uploading (a) our point-by-point response to the comments (below) (response to reviewers), (b) an updated manuscript with blue highlighting indicating changes (Word document).
We would like to express our great appreciation to you and the reviewers for your comments on our manuscript. We treasure the opportunity and wish that you and the reviewers would acknowledge the revised manuscript. Please inform us if you think the manuscript needs to modify again. We can revise the manuscript till you and the reviewers are satisfied. We are looking forward to hearing from you soon.
Best regards,
Author Response File: Author Response.docx
Reviewer 3 Report
This paper very interisting. Buy, I suggest insert more discussion and conclusion its necessary review. Because, its necessary resume.
The abstract, if possible, insert more details about results and describe more details the experiment.
Author Response
Dear Editor,
Thank you for allowing a revision of our manuscript, with an opportunity to address the reviewer’s comments. We have studied the reviewer’s comments carefully and have made revisions marked with the revised format in the manuscript.
We are uploading (a) our point-by-point response to the comments (below) (response to reviewers), (b) an updated manuscript with blue highlighting indicating changes (Word document).
We would like to express our great appreciation to you and the reviewers for your comments on our manuscript. We treasure the opportunity and wish that you and the reviewers would acknowledge the revised manuscript. Please inform us if you think the manuscript needs to modify again. We can revise the manuscript till you and the reviewers are satisfied. We are looking forward to hearing from you soon.
Best regards,
Author Response File: Author Response.docx
Reviewer 4 Report
Manuscript: agronomy-2108866-peer-review-v1
Tiltle: „Summer maize growth estimation based on Near-surface multi source data”
In the manuscript the Authors proposed an accurate method of monitoring maize plants based on LAI and soil plant analytical development (SPAD) values based on the fusion of ground-air multi-source data. The machine learning models and statistical linear regression models were selected for inversion model construction, to obtain inversion models with good generalization ability and accuracy.
I believe that all analytical methods aimed for increasing the crop production are valid and should be distributed. The methods used by the Authors are properly used, well described and presented.
What I miss in this paper is a small paragraph, for example in the discussion section devoted to practical use of the sophisticated analytical methods in practice. Do Authors have any suggestions how their results can be introduced into the practice?. Adding 3-5 sentences on this subject would be nice.
I have some minor remarks and questions concerning the manuscript that I have listed below:
Line 16 – Add LAI acronym in brackets, after the first use of the leaf areal index.
Line 100: A citation of the source of the climate data would be good here.
Fig. 1. Could you explain why in 2020 there is only 5 sampling points on Jinyangguang 6 variety, whereas in 2021 there is a 15 sampling sites for each of the three varieties: Jinyangguang 6, Chunyu 985, and Nongxing 207?. Shouldn`t it be more 1:1 ratio?.
Fig. 1. Does the natural differences between maize varieties can hamper the deep learning model predictions?. Especially in section 2.4 “Construction and Evaluation Method of Summer Maize Growth Parameter Inversion Model”. Please explain.
Line 146-147: “In the two year experiment, the same maize plant as the leaf area measurement was selected as the measurement object…” – How is that possible when maize is an annual plant which usually is being sawed on April-May and harvest on September-October, depending on geographical location and environmental conditions?. Please explain. If you mean that you have reused the data from the same year, please reformulate the sentence.
Lines 514-515: To monitor maize LAI and SPA more quickly and accurately and to obtain an inversion model with better generalization ability.” – This sentence sounds like it was cut in half. Please rephrase it. Probably by combining it with the adjacent sentence “We obtained …”
Line 554: I might be wrong but I believe that the sets of data that the Authors used for developing and training the models should be available to interested parties, e.g. by submitting it to some public data repository, like it is required for e.g. microarray analysis where all raw data need to be deposited in GEO repository.
Kind regards,
The Reviewer
Author Response
Dear Editor,
Thank you for allowing a revision of our manuscript, with an opportunity to address the reviewer’s comments. We have studied the reviewer’s comments carefully and have made revisions marked with the revised format in the manuscript.
We are uploading (a) our point-by-point response to the comments (below) (response to reviewers), (b) an updated manuscript with blue highlighting indicating changes (Word document).
We would like to express our great appreciation to you and the reviewers for your comments on our manuscript. We treasure the opportunity and wish that you and the reviewers would acknowledge the revised manuscript. Please inform us if you think the manuscript needs to modify again. We can revise the manuscript till you and the reviewers are satisfied. We are looking forward to hearing from you soon.
Best regards,
Author Response File: Author Response.docx
