Identification of Characteristic Parameters in Seed Yielding of Selected Varieties of Industrial Hemp (Cannabis sativa L.) Using Artificial Intelligence Methods
Round 1
Reviewer 1 Report
Summary
Authors use neural modelling to predict the hemp yield. Data of two specific species have been collected. Six different ANN models are created and evaluated. In addition sensitivity analysis of variables has been done and features are ranked to find the important indicators. Complete experimentation work has been done in STATISTICA 7.1.
Overall Judgement
Authors only work on ANN modelling. there are many Machine learning models which can be used for prediction. It is advised to give the justification for the same. With in ANN also why only RBF is used. Its justification is also missing.
Architecture and mathematical overview of models used is also needed. Difference in architecture and hyperparameters used in user defined network and automatic design network is also not very clear.
To evaluate the model evaluation metrics are used but again their explanation, significance, formulae are missing.
In the research work 6 models are generated but which one is more appropriate mean comparison among them or with state of art work is missing.
In sensitivity analysis which method of ranking is used. kindly explain and discuss significance of ranking with reference of obtained results in conclusion.
Overall paper need modifications.
Author Response
Dear Reviewer,
Thank you for all of your valuable comments.
The attachment includes the response to the Reviewer’s comments.
Kind regards
The Authors
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Review of the manuscript "Identification of characteristic parameters in seed yielding of selected varieties of industrial hemp (Cannabis sativa L.) using artificial intelligence methods."
Dear Authors,
I have reviewed the manuscript entitled "Identification of characteristic parameters in seed yielding of selected varieties of industrial hemp (Cannabis sativa L.) using artificial intelligence methods" submitted to the Agriculture journal from MDPI. The paper presents an interesting approach to predicting hemp seed yield using artificial neural network (ANN) models. However, I have identified some flaws that need to be addressed before the manuscript can be considered for publication. Here, I outline some of the main concerns and recommend major revisions.
1. Presentation of results: The presentation of the results can be improved. The manuscript would benefit from a more comprehensive and coherent presentation of the findings. I believe that Tables 2, 3, 4, and Figures 2, 3, and 4 can be merged to reduce space and facilitate the comparisons against one another.
2. Methods and data analysis: The methods used in the manuscript are not state-of-the-art in terms of data analysis. Additionally, a comparison of the performance of the proposed ANN models with other shallow learning algorithms like Random Forest, XGB, SVM, etc., would enhance the manuscript's credibility.
3. Sensitivity analysis: The manuscript mentions that a sensitivity analysis was conducted, but the results of this analysis are presented in a table. Would it not be better to present it as a graphic?
4. Future research: The conclusions section mentions that the authors plan to extend the data set with information from the next growing season. It would be beneficial for the authors (in the Discussion section) to discuss the limitations of the current study more and how these limitations could be addressed in future research, including the use of additional data, different modeling techniques, and the integration of other relevant factors that could influence hemp seed yield.
5. Language and grammar: The manuscript requires a thorough language and grammar revision. The Method section needs to be better written with fewer topics and more elaborate text. There are instances of awkward phrasing, incorrect punctuation, and improper word usage throughout the text. Careful proofreading and editing of the manuscript by a native English speaker would greatly enhance its readability and professionalism.
In conclusion, I recommend a major revision of this manuscript. The authors should address the issues outlined above to improve the manuscript's quality and clarity. Once these concerns have been addressed, the manuscript has the potential to make a valuable contribution to the literature on hemp seed yield prediction and the application of artificial intelligence methods in agriculture.
Author Response
Dear Reviewer,
Thank you for all of your valuable comments.
The attachment includes the response to the Reviewer’s comments.
Kind regards
The Authors
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
The authors have improved the manuscript and answered my concerns. I consider the manuscript appropriate for publication.
