Estimating Fuel Consumption of an Agricultural Robot by Applying Machine Learning Techniques during Seeding Operation
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThe paper presents an Estimating fuel consumption of an agricultural robot by applying machine learning techniques. Case: seeding operation.
Although I have no doubt that the results presented are correct and the methodology appropriate, I can not find the no critical discussion is performed on the results for predicting fuel consumption for a tractor model.
Some suggestions to the authors for making they work a more interesting scientific paper:
- Explain more in detail how you draw the 27.5% error with a numerical data using statistical approach for the first model.
- Explain more in detail how you draw the % error with a numerical data using statistical data for the second model not just for developing machine models.
- Please refer the suggestions mentioned on the manuscript.
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThe paper provides valuable insights into the integration of agricultural robots in precision farming and the importance of accurate fuel consumption estimation for sustainable agricultural practices. The utilization of both traditional ASABE models and advanced machine learning techniques demonstrates a comprehensive approach to address this challenge. The thorough evaluation and comparison of different models, along with sensitivity analysis, contribute to the robustness of the findings. However, further discussion on the limitations of the study and potential avenues for future research would enhance the paper's completeness. Overall, this research significantly contributes to the field of precision agriculture and provides practical implications for farmers and stakeholders aiming to optimize fuel usage and improve productivity.
The main question addressed by the research is how to accurately estimate the fuel consumption of an agricultural robot using both conventional methods like the ASABE fuel consumption model and machine learning techniques like Gaussian process regression (GPR).
The parts considered original or relevant for the field include:
- The comparison between conventional fuel consumption estimation models and machine learning-based approaches, highlighting the potential benefits of using more advanced techniques.
- The consideration of specific operational parameters of the agricultural robot, such as total operational time, total traveled distance, automatic working distance, and automatic turning distance, in fuel consumption estimation.
- The identification of significant correlations between certain operational parameters and fuel consumption, providing valuable insights for optimizing robot performance and energy usage. The paper addresses a gap in the field by providing a comprehensive analysis of different methods for estimating fuel consumption in agricultural robots, considering both traditional and advanced modeling approaches.
Compared with other published material, this paper adds:
- A detailed comparison of various machine learning techniques for fuel consumption estimation in agricultural robots, demonstrating the superiority of Gaussian process regression.
= Insightful findings regarding the importance of specific operational parameters in predicting fuel consumption, which can inform decision-making and optimization strategies in agricultural operations.
Specific improvements regarding the methodology that the authors should
consider include:
- Providing more detailed information on the process of feature selection and hyperparameter optimization for the machine learning models.
- Clarifying the criteria used for data cleaning and outlier detection to ensure transparency and reproducibility.
- Including additional controls or sensitivity analyses to validate the robustness of the findings and identify potential confounding factors.
The conclusions are consistent with the evidence and arguments presented in the paper. The authors successfully addressed the main question by comparing different fuel consumption estimation models and conducting experiments to evaluate their performance. All main questions posed were addressed through specific experiments, analyses, and comparisons.
The references appear appropriate and relevant to the subject area. They include a range of studies on fuel consumption modeling, machine learning applications in agriculture, and related topics, supporting the research findings and contextualizing the study within existing literature.
Additional comments on the tables, figures, and data quality:
- The tables and figures provide clear and concise presentation of the data and results.
- The quality of the data appears satisfactory, although more details on data collection procedures and potential sources of error would enhance transparency and reproducibility.
- Providing access to the raw data or detailed descriptions of data sources would allow for better evaluation and verification of the study findings.
Below are some specific comments for your consideration.
- Hyphens are being used inappropriately throughout the manuscripts.
- please rephrase the title so the period only appears at the end, not within the title
- the third paragraph of the intro reviewed a whole list of literature studies, which is good. Please consider adding a summary at the end of what has been done/known in the field
- L109, what is the robot being studied? I do not think readers know at this point.
- No objectives can be found in the intro
- Robot with two diesel engines? could you please provide a rationale for the design principle of this?
- Figure 5, what is the unit of fuel consumption? please add this
Comments on the Quality of English Languageproofreading is required
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsPlease correct minor editing problems mentioned on the manuscript.
Thank you very much for your efforts to improve the quality of the article.
Comments for author File: Comments.pdf
Please improve the quality of English by a professional editor.