Advancing Agricultural Predictions: A Deep Learning Approach to Estimating Bulb Weight Using Neural Prophet Model

Round 1

Reviewer 1 Report

Next, we used the lag model with Neural Prophet instead of statistical analysis for 356 of the measurement data.

an example better to write: The lag model was used with Neural Prophet instead of statistical analysis for 356 the measurement data.

Author Response

Thank you for your comment and suggestion.

We have revised the sentence as per your recommendation to improve clarity. We have also carefully reviewed the entire manuscript to ensure it meets the necessary standards. We are confident that the revisions have addressed the concerns raised by the reviewers and have strengthened the manuscript.

Reviewer 2 Report

This paper proposes a deep learning approach to predict the bulb weight of harvested crops using garlic and onion growth stage measurement data and finally to minimizing fiscal expenditures for related policy authorities while increasing the welfare of farmers and consumers through proactive preparation of supply.

The topic is relevant and original. The authors, in their theoretical work, treated the Neural Prophet Autoregressive Exogenous-variable (ARX) model. Then, they will use it in predicting the bulb weight of harvested crops.

 The documentation is appropriate.

The results are well explained with adequate discussion. The authors designed the study to train the Neural Prophet lag model with the data from 2020 and 2021 and then predict the bulb weight from April to June in 2022. The estimated results were based only on the growth measurement data, even though no other growth information (such as weather data or growth indices) was included as independent variables. So, to make useful the proposed application, in the future must get more data. As the authors specified, an initial statistical processing of the data and additional information on crop production are required.

In conclusions ‘section the authors emphasise their contributions and future possible applications.

The references are appropriate and recent.

 Final recommendation:

The paper provides an interesting and usefully research work with future using. The subject is well within the scope of the journal, and the paper fulfils all the requirements to be published.

Author Response

Thank you for your comment. We appreciate your recognition of our efforts to improve the manuscript. We are committed to continuously developing and enhancing our research to further increase the performance and accuracy of our model. As we progress, we will take into consideration the valuable feedback provided by the reviewers, ensuring that our work remains aligned with the highest standards of quality and rigor.

Reviewer 3 Report

In abstract sentence formation need to be improved.

The heading 5. Estimated Results better to change. Meaning getting different from that title.

Number of references can be increased to 15 as minimum.

Author Response

Thank you for your valuable comments. We have made the following revisions to the manuscript based on your suggestions:

1. Improved the abstract by refining sentence formation for better clarity and readability.
2. Revised the heading "Estimated Results" to reflect the section's content better, now titled "Performance Evaluation"
3. Added more relevant references, ensuring that the total number of citations meets the minimum requirement of 15.

We appreciate your constructive feedback, which has helped improve the quality of our manuscript. We hope these revisions address your concerns and that the manuscript is now suitable for publication.

Reviewer 4 Report

1. Many places seen units are not kept. Kindly look into this matter.
2. Table 1. Nomenclature and description of parameters and variables should be kept before the introduction. So that reader can directly see from there.
3. Gaps of the earlier study and this study and highlight the motivation of this work in the introduction section
4. Many old references cited in the MS may be completely removed and add new ones
5-References 4-8 are not valid because of language.
6. Ensure that your manuscript is well edited for English language and technical expressions
7. All references according to the journal format.
8. Many useless full stops, the comma should be deleted and given in the appropriate format.
9. Some spelling mistakes are also seen, kindly rectify the same.
10. Same references are cited many times. Hence, I will provide you a good set of references for your needful use. Kindly use this reference.
11. Please improve Figure 1 TO 7.
12. Kindly count the sentences of the Highlights, it should be according to the journal guidelines.
13.More articles should be discussed, especially among the international literature.
14. What are the original, novelty, or unique ideas behind this research as compared to previous research/other reported work? Why it is worth knowing?

The abstract does not satisfy with publication standard as shown below;

Does the abstract summarize the paper's objectives, main thrust and major conclusions? Please consider whether or not the Abstract conveys clearly the purpose of the study, provides a balanced and accurate depiction of the key findings, and addresses the implications of the work for spatial information Science. Could a person read the abstract and get a clear sense of what the article will be about? Will the key words enable other professionals to locate the work with the search engines commonly used by academic libraries? What about the conclusion? Does the manuscript give a sense of revisiting the main ideas briefly? Does it give the reader a feeling that all of the ideas have been tied together?

The abstract does not satisfy with publication standard as shown below;
Abstract is too long. Please provide an abstract of 150 to 200 words.

Check if you have included enough details on statistics (number of replicates, statistical tests performed, presentation of average and standard deviation or error values, both in tables and graphs), and complete it if needed.

Check if you have included self-explanatory captions for all tables and graphs, and complete and/or correct it if needed.

Check your whole manuscript for any typo and for English expression, in order to prevent this kind of mistakes.

Author Response

Thank you for the comments and suggestions; we appreciate your time and consideration. In the attached response, we express the corrections.

Author Response File: Author Response.docx

Reviewer 5 Report

The topic is a good representation of ANN application. The methodology can be upgraded with the existing also open source R, Python based solutions. With the comparisation of existing open source solution the selection of the Neural Prophet Model would be more understandable. I suggest the enlarge the literature and citation. The current article focus mainly the selected model. Overall the article is a nice representation of the applied agriculture IT.

Author Response

Thank you for the response to our research. I have made the following adjustments to the manuscript:

1. I have expanded the literature review section by including additional citations and further discussions of relevant studies, which provide a more comprehensive understanding of the research context.

2. Upon acceptance of the paper, I will make the Neural Prophet (NP) source code publicly available on GitHub, allowing other researchers to access, reproduce, and build upon our work.