Digitization of Crop Nitrogen Modelling: A Review
Round 1
Reviewer 1 Report
Abstract
I missed the methodology used. Search engine, criteria ...
Introduction
The authors divided the article into sections. However, I still think it should follow the standard model, where we have: Introduction, Material and methods, Results and discussion, Conclusion.
Line 83 – 92 - I recommend rearranging the article and following the classic form. Considering the change, this part refers to material and methods.(RQ1, …RQ5).
Line 103-104 - Dear authors, it got a little confusing. Of course, it is not just nitrogen that causes spatial variability in crop productivity. There are numerous factors such as physical and chemical attributes of the soil, phenological indices of the crop, physiology of the crop, climate variation, available water, etc. Please make this clearer in this part of the text.
Line 165 - Do the authors mean that it is ideal to keep sandy soil with "average" moisture between field capacity and "soil wilting point"? OK. Hence the Nitrogen becomes more available.
Will in this way the plant will exert its maximum physiological activity? Will the plant in this condition produce at its maximum efficiency?
Line 233 - Soil waterlogging is the same as water stress from overwatering via precipitation or irrigation. This last term is more technical and I believe fits better in the text.
Line 295 - This has already been mentioned on line 46. Repeated.
There are 2 Tables 3 in the text. Adjust table numbers.
Conclusion:
Line 589 - models after their calibration and validation are influenced by location. I believe it is interesting to report differences, mainly in temperature, between equatorial, tropical, subtropical, desert, temperate, Mediterranean, semi-arid, cold (or subpolar), mountain cold and polar climates. That these different climates interfere significantly in the studied models.
Comments for author File: Comments.pdf
Author Response
Dear Reviewer,
Agronomy
Please find attached the responses point-by-point to your suggestions to the manuscript "Digitization of crop nitrogen modelling: A Review.".
All modifications were made in accordance to your consideration and the responses to your suggestions are also attached below. We would like to thanks for your effort and time dedication to evaluate our manuscript. In our opinion,
significant modifications were carried out across the manuscript allowing us to improve considerably our work.
All the document has been revised to improve the English and make it more correct and readable.
Thanks for your attention.
Yours sincerely,
Mrs. Luís Silva
Author Response File: Author Response.pdf
Reviewer 2 Report
The paper discusses the importance of applying the correct dose of nitrogen (N) fertilizer to crops and highlights the use of predictive models to optimize N application. It acknowledges that current models integrate information about soil, climate, crops, and agricultural practices to predict N requirements. Furthermore, it emphasizes the recent advancements in remote sensing technology, which contribute to digital modeling of crop N requirements and enable real-time adjustments for increased accuracy in nutrient application. Overall, this study provides a clear overview of the subject matter, emphasizing the importance of accurate N fertilizer application and the role of predictive models and digital technologies in achieving this goal.
There are some minor issues that should be addressed before publication.
1. Line 53-55. This sentence lacks reference. Could cite Liu et al. 2023.
Liu, K., Harrison, M.T., Yan, H. et al. Silver lining to a climate crisis in multiple prospects for alleviating crop waterlogging under future climates. Nat Commun 14, 765 (2023). https://doi.org/10.1038/s41467-023-36129-4
2. I would suggest reducing the length of N dynamics as this section is already well-known and reported by many similar lit review. Authors should pay closer attention to the section of “Crop N modelling” which is the hot-spot areas nowadays.
3. Table 2. No one would say APSIM- trigo but APSIM-wheat
4. in fact, another important area: integration of crop modelling and machine learning is not reviewed here. See the papers below
https://arxiv.org/abs/2207.03270 gym-DSSAT: a crop model turned into a Reinforcement Learning environment
https://arxiv.org/abs/2204.10394 Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations
NA
Author Response
Dear Reviewer,
Agronomy
Please find attached the responses to your comments and suggestions of the manuscript entitled “Digitization of crop nitrogen modelling: A Review”. All
modifications were made in accordance with your consideration. We would like to thanks for the review effort and dedicated time to evaluate our manuscript. In our opinion, significant modifications were carried out across the manuscript allowing us to improve considerably our work.
Thanks for your attention.
Yours sincerely,
Mrs. Luís Silva
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Line 608 - models after calibration and validation are influenced by location. I find it interesting to report the differences, mainly in temperature, between the equatorial, tropical, subtropical, desert, temperate, Mediterranean, semi-arid, cold (or subpolar), cold mountain and polar climates. That these different climates interfere significantly in the studied models.
N
Author Response
Dear Reviewer,
Agronomy
Please find attached the revised version of the manuscript entitled “Digitization of crop nitrogen modelling: A Review.”.
All modifications were made in accordance to your consideration and the response to the suggestion is attached below. We would like to thanks for your effort and dedicated time to evaluate our manuscript. In our opinion, significant modifications were carried out across the manuscript allowing us to improve considerably our work.
Thanks for your attention.
Yours sincerely,
Mr. Luís Silva
Author Response File: Author Response.pdf