Review Reports - Modification of Values for the Horizontal Force of Tillage Implements Estimated from the ASABE Form Using an Artificial Neural Network

Round 1

Reviewer 1 Report (New Reviewer)

1. Lack of clarity in the objectives: The paper does not clearly state the specific objectives of the study. It is important to clearly define the research question or objective that the authors aim to address.

2. Limited explanation of the methodology: The paper lacks a detailed description of the methodology employed to modify the values of the horizontal force. The authors should provide more information on the specific steps taken to calibrate the Fi parameter using a regression technique and establish the feed-forward artificial neural network (ANN) model.

3. Insufficient justification for the inputs used in the ANN model: The paper mentions four inputs used in the ANN model: working field criterion, soil texture norm, initial soil moisture content, and the horizontal force estimated by the ASABE standard. However, the rationale for selecting these specific inputs is not adequately explained. The authors should provide a clear justification for their choice of inputs and explain how these inputs contribute to the accuracy of the model.

4. Lack of comparison with other methods/models: The paper does not provide a comparison of the proposed ANN model with other existing methods or models for estimating horizontal force. Without such a comparison, it is difficult to assess the novelty and effectiveness of the proposed approach. The authors should include a discussion on how their ANN model performs in comparison to other relevant approaches.

5. Limited generalizability of results: The study focuses on disk, chisel, and moldboard plows, but it is not clear if the findings can be generalized to other types of tillage implements. The authors should discuss the limitations and applicability of their model to different types of implements, highlighting potential challenges or variations in performance.

6. Inadequate statistical analysis: The paper mentions the coefficient of determination (R2) values for the ANN model in the training, testing, and validation stages. However, it does not provide any statistical analysis or significance testing to support the reported results. The authors should provide additional statistical analysis, such as confidence intervals or hypothesis testing, to establish the reliability and significance of their findings.

7. Lack of discussion on limitations and future directions: The paper does not adequately address the limitations of the proposed approach or discuss future directions for improvement. It is important to acknowledge the limitations of the model, such as the assumptions made or potential sources of error, and suggest areas for further research or refinement.

8. Insufficient details on the Excel spreadsheet: The paper briefly mentions the creation of an Excel spreadsheet for estimating the horizontal force of specific tillage implements. However, there is a lack of information on the functionality, usability, and validation of the spreadsheet. The authors should provide more details on how the spreadsheet was developed, tested, and how it can be utilized by agricultural engineers.

9. Why was ANN chosen over other algorithms? You may add comparison of ANN with other algorithms by referring to ‘A machine learning approach for vibration-based multipoint tool insert health prediction on vertical machining centre (VMC),’ ‘Application of metaheuristic optimization based support vector machine for milling cutter health monitoring,’ ‘Augmentation of Decision Tree Model Through Hyper-Parameters Tuning for Monitoring of Cutting Tool Faults Based on Vibration Signatures’

Moderate editing of English language required

Author Response

Response to Reviewer #1

General Comment:

Moderate editing of English language required

Dear reviewer,

Thank you so much for your positive and valuable comments. We would like to inform you that we made English editing of our paper through mpdi office. The certificate is attached here.

Comments and Suggestions for Authors

Point #1

Lack of clarity in the objectives: The paper does not clearly state the specific objectives of the study. It is important to clearly define the research question or objective that the authors aim to address.

Response on point #1

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

In the revised manuscript, we re-arrange the end of the introduction section to clear the objectives at the end on introduction section “Hence, the main objectives of this research are the following: (1) to create a regression model that can predict the soil texture adjustment parameter (Fi) that is used in ASABE form [7]; (2) to develop an ANN model to modify the values of the draft force of tillage implements that are estimated from the form of ASABE [7], and which are based on a wide range of working variables; (3) to obtain the results from a statistical performance evaluation with an ANN model, and to achieve the importance of certain predictor variables; and (4) to create a useful Excel spreadsheet to serve as an easy tool through which to obtain the values of the modified draft force of tillage implements that are based on wide range of working variables. However, the end of the introduction section became as follows:

“ To the best of our knowledge, despite extensive literature examination, no study on the prediction of the soil texture adjustment parameter (FI) has been used in ASABE form [7]. In addition, this method being used to modify the values of the draft force of tillage implements, as estimated from the form of ASABE [7] by using an ANN model, has also not been tested yet. The importance of conducting this research lies in the fact that the draft force is a vital factor in determining the energy requirements of tillage implements for various purposes, including cost analysis, fuel consumption prediction, and matching agricultural tractors with the correct tillage implements. The ability to accurately predict the modified draft force of tillage implements, based on ASABE form [7], through the use of machine learning models such as ANN can help in producing better farm machinery management and utilization of the available resources. Furthermore, an accurate prediction draft force can also aid in mitigating the potential of using tillage implement management approaches that are associated with consuming diesel fuel, which is a significant concern in many parts of the world. By accurately predicting the draft force of tillage implements, farm machinery engineers can determine the variables that will offer less draft force for tillage implements when conducting tillage operation on a specific soil texture. This is possible because the user can change tractor power, tillage speed, tillage depth, implement width, soil bulk density, and soil moisture content as needed to achieve a lower energy for the plowing process. Conducting this research in the study area is necessary because the draft force of tillage implements can vary significantly depending on the specific soil texture and other factors. Therefore, it is essential to develop models that are tailored to the unique characteristics of the study area to achieve accurate predictions, or so that they can be used in many parts of the world. Moreover, the novelty of the paper lies in developing a new soil texture parameter that can address the effect of soil texture on the draft force of tillage implements. Hence, the main objectives of this research are the following: (1) to create a regression model that can predict the soil texture adjustment parameter (Fi) that is used in ASABE form [7]; (2) to develop an ANN model to modify the values of the draft force of tillage implements that are estimated from the form of ASABE [7], and which are based on a wide range of working variables; (3) to obtain the results from a statistical performance evaluation with an ANN model, and to achieve the importance of certain predictor variables; and (4) to create a useful Excel spreadsheet to serve as an easy tool through which to obtain the values of the modified draft force of tillage implements that are based on wide range of working variables.”

Point #2

Limited explanation of the methodology: The paper lacks a detailed description of the methodology employed to modify the values of the horizontal force. The authors should provide more information on the specific steps taken to calibrate the Fi parameter using a regression technique and establish the feed-forward artificial neural network (ANN) model.

Response on point #2

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

In the materials and method section and under section 2.2. (The Methodology Steps of This Study), we explain how we get the soil texture norm (STN, dimensionless), which combines all the soil contents of sand, silt, and clay using Eq.4. Then we referred to the values of Fi parameter according to values from ASABE [7] in Table 2. Furthermore, we assigned values of the Fi parameter according to values from ASABE [7] according to the soil texture; however, Table (3) shows the assigned values of the Fi parameters that were used in our data to create a regression model to predict a new Fi parameter based on soil texture norm (STN). However, we arranged the data in two columns in Excel, column for Fi parameter based on soil texture and column for Fi parameter according to values from ASABE [7]. We tested all the fit function in Excel and we found that the following formula was the best (Eq. 5).

To predict the modified draft force of certain tillage implements with an ANN model, we created the working field criterion (WFC) to combine all working parameters; these are denoted by tractor power (TP, kw), initial soil bulk density (BD, g/cm³), tillage depth (d, cm), tillage speed (S, km/h), and plow width (L, cm) as appeared in Eq. (6) . In addition, the research steps to obtain the modified horizontal force with the ANN model are as follows:

1.	Collecting the clay content in the soil (percentage), sand content in the soil (percentage), and silt content in the soil (percentage);
2.	Calculating the STN with Eq. (4);
3.	Calculating the new Fi parameter with Eq. (5);
4.	Collecting the tillage depth (d, cm), tillage speed (S, km/h), tractor power (TP, kW), initial soil bulk density (BD, g/cm³), the plow width (cm) for disk and moldboard plows, and the no. of tools for chisel plows;
5.	Calculating the WFC with Eq. (6);
6.	Selecting the parameters in Eq. 1 for chisel plows (Table 2) as follows: No. of tools, A=91, B=5.4, C=0, tillage speed, and tillage depth;
7.	Calculating the horizontal force estimated from Eq. 1 using the new Fi parameter for the chisel plows;
8.	Selecting the parameters in Eq. 1 for the moldboard plow (Table 2) as follows: A=652, B=0, tillage speed, tillage depth, and plow width;
9.	Calculating the horizontal force estimated from Eq.1 using the new Fi parameter for moldboard plows;
10.	Selecting the parameters in Eq. 1 for disk plows (Table 2) as follows: A=124, B=6.4, C=0, tillage speed, tillage depth, and plow width;
11.	Calculating the horizontal force estimated from Eq. 1 using the new Fi parameter for disk plows.

In the text, we insert “However, we arranged the data in two columns in Excel, column for Fi parameter based on soil texture and column for Fi parameter according to values from ASABE [7]. Then we tested all the fit functions in the Excel spreadsheet and we found that the following formula was the best”

Point #3

Insufficient justification for the inputs used in the ANN model: The paper mentions four inputs used in the ANN model: working field criterion, soil texture norm, initial soil moisture content, and the horizontal force estimated by the ASABE standard. However, the rationale for selecting these specific inputs is not adequately explained. The authors should provide a clear justification for their choice of inputs and explain how these inputs contribute to the accuracy of the model.

Response on point #3

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

We insert” Numerous research papers claimed that the draft force of tillage implements are affected by many variables namely: soil texture, soil moisture content, tillage depth, tillage speed, tractor power, soil bulk density, implement width, etc. Thus in our research, we combined most of these variables in one variable called working field criterion (WFC) and other variables like soil texture and soil moisture content were considered as inputs, besides, the important input was the draft force which was determined by the new Fi parameter. However, these variables were considered to be four inputs to predict the modified draft force of tillage implements” in the text to justify for the inputs used in the ANN model. We have not explain how the investigated inputs contribute to the accuracy of the model, due to all the inputs have clear effect on the draft force of the tillage implements, However, in section 3.4. Examining the Effects of Independent Input Variables in the results and discussion section, we explain how the investigated inputs contribute to the ANN model output.

Point# 4

Lack of comparison with other methods/models: The paper does not provide a comparison of the proposed ANN model with other existing methods or models for estimating horizontal force. Without such a comparison, it is difficult to assess the novelty and effectiveness of the proposed approach. The authors should include a discussion on how their ANN model performs in comparison to other relevant approaches.

Response on point #4

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

In the results and discussion section, we wrote, “Various studies are available on the draft force, which is modeled by ANN method, for tillage implements [82]; however, the former ANN modeling approaches have not attempted to modify the draft force of ASABE draft form [7]. Hence, the authors of this paper present this applied ANN model for predicting the modified draft force of the famous primary tillage implements that are used for farm machinery management purposes. Compared to other studies, the present work stands alone with a novel approach; it has significant value in formulating the soil Fi parameter used by ASABE [7} for the purposes of draft determination and for modifying the famous draft force that is detailed in the ASABE form [7].

Point #5

Limited generalizability of results: The study focuses on disk, chisel, and moldboard plows, but it is not clear if the findings can be generalized to other types of tillage implements. The authors should discuss the limitations and applicability of their model to different types of implements, highlighting potential challenges or variations in performance.

Response on point #5

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

We added” There was no limitations and applicability of the investigated ANN model to different types of farm implements. However, the potential challenges or variations in the performance will be depended on the quality and quantity of the training data used.

Point# 6

Inadequate statistical analysis: The paper mentions the coefficient of determination (R2) values for the ANN model in the training, testing, and validation stages. However, it does not provide any statistical analysis or significance testing to support the reported results. The authors should provide additional statistical analysis, such as confidence intervals or hypothesis testing, to establish the reliability and significance of their findings.

Response on point #6

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

In most of research papers, which focused on ANN modeling, the statistical evaluation using some criteria such as RMSE, MAE, R2, etc. are preferred to show the strength of the ANN model in its ability to find the relations between inputs and outputs.Thus, in the training, testing, and validation stages, we get performance evaluation parameters for predicting the modified horizontal force of the established ANN as described in Table 8. We also appreciate the suggestion to include statistical analysis measures such as confidence intervals or hypothesis testing, to establish the reliability and significance of their findings. However, we made some statistical description of our data in Table (4). We also respectfully disagree with include statistical analysis such as ANOVA in our study due to the main aim of our study was to create an ANN model to predict the modified draft force of some tillage implements.

Point #7

Lack of discussion on limitations and future directions: The paper does not adequately address the limitations of the proposed approach or discuss future directions for improvement. It is important to acknowledge the limitations of the model, such as the assumptions made or potential sources of error, and suggest areas for further research or refinement.

Response on point #7

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

In the text, there were different limitations in results and discussion section as follows:

“However, the model’s limitations must be considered when interpreting its results.”

“ There was no limitations and applicability of the investigated ANN model to different types of farm implements.” However, the potential challenges or variations in the performance will be depended on the quality and quantity of the training data used.

“There are also limitations in using ANN models for predicting the draft force of tillage implements and other parameters [81]. The accuracy of the ANN model is contingent on the quality and quantity of the training data used [81]. Additionally, the model’s accuracy may decrease when applied to data with significant differences from the training dataset [81].

Point #8

Insufficient details on the Excel spreadsheet: The paper briefly mentions the creation of an Excel spreadsheet for estimating the horizontal force of specific tillage implements. However, there is a lack of information on the functionality, usability, and validation of the spreadsheet. The authors should provide more details on how the spreadsheet was developed, tested, and how agricultural engineers can utilize it.

Response on point #8

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

The functionality and usability of the spreadsheet were addressed through inserting the required equations from 12 to 22 and we gave numeric example how to get the modified draft force for a moldboard plow using specific data (table 9) and validation of the spreadsheet was evaluated by calculating the percentage error using Eq.23 . In addition, the developed Excel spreadsheet screen shot was inserted previously in the text and we removed it based on the suggestion of another reviewer. In the text, we added” However, a screen capture of the developed worksheet templet for the determination of the modified horizontal force using ANN model is shown in Figure 5.

Point #9

Why was ANN chosen over other algorithms? You may add comparison of ANN with other algorithms by referring to ‘A machine learning approach for vibration-based multipoint tool insert health prediction on vertical machining center (VMC),’ ‘Application of metaheuristic optimization based support vector machine for milling cutter health monitoring,’ ‘Augmentation of Decision Tree Model Through Hyper-Parameters Tuning for Monitoring of Cutting Tool Faults Based on Vibration Signatures’

Response on point #9

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

The paper analyzed here deals with the use of ANN model to determine the draft force of some tillage implements. This problem was intensively investigated in the past decade using also ANN technique. I analyzed the newly proposed model presented here based on the new inputs, and I concluded that the actual model is not presented earlier.

Author Response File: Author Response.pdf

Reviewer 2 Report (Previous Reviewer 1)

The manuscript entitled

"Modification of Values for the Horizontal Force of Tillage Implements Estimated from the ASABE Form using an Artificial Neural Network “ (Manuscript ID: applsci-2433793)

is another slightly revised version of the publication I am reviewing (Manuscript ID: applsci-2285457). The Authors referred to my previous remarks, but avoided answering the essential issues.

My answer to the question in the review form "Is the research design appropriate?" is negative.

I still believe that the Authors made methodological errors regarding:

1) The method of carrying out experimental research

2) The method of developing the ANN model

The above errors make the entirety of the article wrong. Poorly designed studies cannot produce correct results.

Detailed comments can be found in the pdf file.

Comments for author File: Comments.pdf

Author Response

Response to Reviewer #2

General

Point #1

Does the introduction provide sufficient background and include all relevant references (Not applicable).

Response one point #1

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

We added in the introduction section” Moreover, draft requirement of tillage implement is essential for appropriate tractor implement matching, and guess of fuel consumption at different operation conditions [6]. The draft of a tillage implement is affected by soil physical properties such as dry bulk density and soil moisture content, tillage speed and tillage depth [7]. However, reducing the draft force of tillage implements has continuously been one of the most vital aims of researchers [8]. Thus, it is highly important to select the operation parameters and the implements used to cultivate agricultural products [9].

Point #2

Are all the cited references relevant to the research? (Not applicable).

Response one point #2

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

We added in the introduction section” The high price of measuring devices and field experiments to acquire draft data of a tillage implement can support to develop a model to estimate such data .The deployment of these models will facilitate an overall reduction of data collection costs and the optimization of the affecting variables. When the measurement of performance indicators for tillage implements such as draft force is not accurate, the recorded draft data are incorrect and will therefore give a different from the performance of the agricultural machine [11].

Point #3

Is the research design appropriate? (Must be improved)

Response one point #3

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

We added “In the first and second experimental sites, the chisel plow under study was mounted at the rear of Ford tractor (main tractor) model TW15 with a diesel engine of 110 kW at 2300 rpm with help of three-point hitch of the tractor. A hydraulic dynamometer (pull type) was attached to the front of Ford tractor. An auxiliary tractor Lamborghini tractor model 1106 with a diesel engine of 110 kW at 2500 rpm was used to pull the chisel plow mounted through dynamometer. The auxiliary tractor pulled the chisel plow mounted tractor in neutral gear with the implement in operating condition. The idle draft force was also recorded in the same field when chisel plow was in lifted position. The difference draft at operating and idle condition gave the draft required to pull the chisel plow. The tillage operation was repeated for all the investigated runs and draft data for each run was recorded. A Kubota M1 tractor (70 kW) and Belarus (67 kW) were used as main and auxiliary tractors, respectively, at the first experimental site. In the materials and method section.

Point #4

Are the methods adequately described? (Must be improved)

Response one point #4

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

We improved the text in the next answerers.

Point #5

Are the conclusions supported by the results? (Not applicable).

Response one point #5

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

In conclusion section , we added “Furthermore, we can recommended to use the ASABE form to estimate the draft force for a tillage implement by replacing Fi parameter with the new Fi parameter developed in this study as the new Fi parameter for soil texture is now measurable.”

Comments and Suggestions for Authors

The manuscript entitled

"Modification of Values for the Horizontal Force of Tillage Implements Estimated from the ASABE Form using an Artificial Neural Network “ (Manuscript ID: applsci-2433793) is another slightly revised version of the publication I am reviewing (Manuscript ID: applsci-2285457). The Authors referred to my previous remarks, but avoided answering the essential issues. My answer to the question in the review form "Is the research design appropriate?" is negative. I still believe that the Authors made methodological errors regarding. From the pdf attached file

Point #1

The method of carrying out experimental research

Response one point 1

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

Yes the measurement of the pulling force was carried out according to the diagram in the figure below:

In our field experiments, we measured the draft force by applying the following procedure. In the first and second experimental sites, the chisel plow under study was mounted at the rear of Ford tractor (main tractor) model TW15 with a diesel engine of 110 kW at 2300 rpm with help of three-point hitch of the tractor. A hydraulic dynamometer (pull type) was attached to the front of Ford tractor. An auxiliary tractor Lamborghini tractor model 1106 with a diesel engine of 110 kW at 2500 rpm was used to pull the chisel plow mounted through dynamometer. The auxiliary tractor pulled the chisel plow mounted tractor in neutral gear with the implement in operating condition. The idle draft force was also recorded in the same field when chisel plow was in lifted position. The difference draft at operating and idle condition gave the draft required to pull the chisel plow. The tillage operation was repeated for all the investigated runs and draft data for each run was recorded. A Kubota M1 tractor (70 kW) and Belarus (67 kW) were used as main and auxiliary tractors, respectively, at the first experimental site.

Note” we added this part to the text”

Point #2

The method of developing the ANN model

I do not understand why the Authors use ANN to determine the DD-AHF (determined during experimental measurements) using the values of the parameters calculated in the equations (WFC, STN, DD) as inputs to the neural network. From equations 1 and 5, the values of DD were calculated (with the Fi parameter - Eq.5 modified by the Authors). Why was the Fi parameter modified if the pulling force calculated using it is incorrect and must be corrected by the ANN model?. Taking other inputs would be a more appropriate approach. Of course, the ANN model is and will be unsuitable due to the use of data from poorly conducted field.

Response one point #2

Dear reviewer,

Thank you so much for your positive and valuable comments. We have incorporated almost all of your suggestions throughout the corrected manuscript.

By answering the point # 1, now it is clear that the use of data was acceptably as the conducted field experiments were achieved properly.
The ANN model was used to determine draft force of some tillage implements due to nonlinear relationship among affecting variables and draft force as described in different research papers. We shorten some affecting variables in one variable called WFC, the STN was represented soil texture, soil moisture content, and calculated draft force (DD using ASABE form by the modified Fi parameter) were acted as inputs. The following Table depicts some numerical data for inputs, measured draft force (output), and predicted modified horizontal force using the developed ANN model (target). (Not this table was added to the revised manuscript under Table 8)

Inputs				Output
Inputs				Measured Draft force in the field experiments or from previous studies (kN)	Predicted or target ( modified Horizontal force (kN)
WFC (--)(combined different variables)	STN (--)(representing soil texture)	MC (%) soil moisture content)	DD (kN) Calculated using ASABE form by the modified Fi parameter)
0.019	0.042	6.31	3.49	6.15	6.55
0.075	0.105	7.34	16.47	11.00	11.92
0.036	0.105	7.34	23.68	15.90	14.87
0.152	0.105	7.34	7.69	5.54	5.07
0.073	0.105	7.34	11.05	8.33	8.47
0.095	0.105	7.34	8.32	6.56	6.19
0.046	0.105	7.34	11.96	9.60	9.51
0.031	0.105	7.34	13.08	10.58	10.80
0.050	0.105	7.34	9.88	8.01	7.96
0.065	0.105	7.34	9.10	7.41	7.04
0.024	0.105	7.34	14.20	11.92	11.91
0.108	0.457	8.26	19.55	16.30	16.50
0.053	0.457	8.26	13.67	15.41	15.35
0.065	0.042	11.58	1.87	3.25	3.51
0.126	0.030	13.82	10.45	16.67	16.54
0.074	0.030	13.82	10.99	18.15	18.66
0.058	0.030	13.82	11.51	19.06	19.15
0.463	0.596	14.69	3.14	2.19	2.71
2.232	0.596	14.69	1.72	1.30	0.95
0.277	0.596	14.69	4.06	3.15	3.58
1.339	0.596	14.69	1.84	1.62	1.61
2.328	0.596	14.69	0.42	0.38	0.63

In the text, we mentioned the DD is the famous empirical model for draft force estimation is the ASABE model [7] and it was estimated by the modified Fi parameter. We modified the Fi parameter - Eq.5 by the Authors to make it measurable rather than assumed by the ASABE. Thus, DD is re calculated using this parameter. However, the draft is affected by DD besides the other variables (WFC, STN, and MC). The output parameter from ANN model was called the modified horizontal force (MHF). In the text we differentiated between DD and MHF.

We think these answers make no errors in the deigned procedure making the entirety of the article not wrong.

Author Response File: Author Response.docx

Reviewer 3 Report (New Reviewer)

This review manuscript entitled Modification of Values for the Horizontal Force of Tillage Implements Estimated from the ASABE Form using an Artificial Neural Network is well written. However, i noticed that the authors dis some work in this study and no idea why to submit it as a review paper? why their results is not used to well compare the current available data? I noticed that the results is weak compared with previous available data. Recommendation is not well supporting the conclusion. A table to compare the value of the additive value/s of this modification can make it easier for audiences.

what is the economical - cost/environmental benefit of this modification?

English language is fine. Authors can improve the scientific writing in some parts. Shorten some long sentences.

Author Response

Response to Reviewer #3

General Comment:

Point #1

Minor editing of English language required .

Response on point #1

Dear reviewer,

Thank you so much for your positive and valuable comments. We would like to inform you that we made English editing of our paper through mpdi office. The certificate is attached here.

Point #2

Does the introduction provide sufficient background and include all relevant references (Can be improved).

Response on point #2

Dear reviewer,

Thank you so much for your positive and valuable comments.

We added some new references in the introduction to clear the importance of draft force determination during tillage operation.

Point #3

Is the research design appropriate? (Can be improved).

Response on point #3

Dear reviewer,

Thank you so much for your positive and valuable comments.

We improved the section of materials and method by explaining how we get the draft force values during field measurements. Also, we added “However, we arranged the data in two columns in Excel, column for Fi parameter based on soil texture and column for Fi parameter according to values from ASABE [7]. Then we tested all the fit functions in the Excel spreadsheet and we found that the following formula was the best:” This to show how we ger the new Fi parameter.

Point #4

The results clearly presented? (Can be improved)

Response on point #4

Dear reviewer,

Thank you so much for your positive and valuable comments.

We added new table to show some numerical data (Table 8) in the results and discussion section to clear the differences among input and output variables.

Point #5

Are the conclusions supported by the results? (Can be improved)

Response on point #5

Dear reviewer,

Thank you so much for your positive and valuable comments.

In abstract section we added” Furthermore, we can also concluded that the equations presented in this study can be formulated by any of computer language to create a simulation program to predict the horizontal force requirements of a tillage implement.

In conclusion section we added “ Furthermore, we can recommended to use the ASABE form to estimate the draft force for a tillage implement by replacing Fi parameter with the new Fi parameter developed in this study as the new Fi parameter for soil texture is now measurable.”

Comments and Suggestions for Authors

Point #1

Response to Point #1

Dear reviewer,

Thank you so much for your positive and valuable comments. This paper is not a review paper but it is an article paper and may be submitted in wrong issue , thus we will correct this with the editor to be article paper.

Point #2

Why the results are not used to well compare the current available data? I noticed that the results is weak compared with previous available data.

Response to Point #2

Dear reviewer,

Thank you so much for your positive and valuable comments. We compared the predicted draft with measured draft and some statistical criteria were observed and presented in table 9. Due to the procedures were different compared with other pervious data, so, we are unable to compare our results with others, but in general, when discussing correlation among variables we compared the results with other previous data and the trend was in agreement.

In the text we wrote”

” The Pearson's correlation coefficients between the explanatory variables were determined prior to creating the ANN model, as is shown in Table 7. The correlation coefficients between the input parameters are relatively low, as is seen in Table 5. There was just a slight negative correlation, with a coefficient value of r=-0.559, between the working field criterion and the horizontal force that was estimated by Eq. (1) when using the new Fi parameter. This was due to the working field criterion being constituted of five variables (tractor power, soil bulk density, tillage depth, tillage speed, and implement width), all of which exhibit a strong effect on the horizontal force requirements of tillage implements, as is shown in previous studies [66-70]. Additionally, we observed the moderate positive correlation, with a coefficient value of r=0.544, between the soil texture norm and horizontal force estimated by Eq. (1). However, the positive correlation (r=0.347, Table 5)—between the initial soil moisture content and the horizontal force estimated by Eq. (1) when using the new Fi parameter—indicates that that moisture content has a direct relation with the horizontal force estimated by Eq. (1). This same trend was observed in previous studies [71,72]. However, in other research papers [66, 73,74], the inverse relationship between the initial soil moisture content and horizontal force was observed. The drop in horizontal force caused by increased soil moisture content can be attributable to both the change in soil resistance and the decrease in soil failure force [66]. Soil texture has a clear effect of a draft force; however, when compared to sandy soil, Novak et al. [75] found that a cultivator's horizontal force increased by around 30% when working in clayey soil. Additionally, according to Chen et al. [76], sandy loamy soil has the greatest values and coarse sand soil have the lowest values of horizontal force with a broad sweep plow. The study's findings show that increasing the working field criterion causes the modified horizontal force to decrease, while increasing the soil texture norm and initial soil moisture content causes the modified horizontal force to grow.

Point #3

Recommendation is not well supporting the conclusion.

Response to Point #3

Dear reviewer,

Thank you so much for your positive and valuable comments.

In conclusion section, we added” Furthermore, we can recommended to use the ASABE form to estimate the draft force for tillage implements by replacing Fi parameter with the new Fi parameter developed in this research paper as the new Fi parameter for soil texture is now measurable”.

Point #4

A table to compare the value of the additive value/s of this modification can make it easier for audiences.

Response to Point #4

Dear reviewer,

Thank you so much for your positive and valuable comments.

The following Table was added to the text to depict some numerical data for inputs, measured draft force (output), and predicted modified horizontal force using the developed ANN model (target). (Not this table was added to the revised manuscript under Table 8).

Inputs				Output
Inputs				Measured Draft force in the field experiments or from previous studies (kN)	Predicted or target ( modified Horizontal force (kN)
WFC (--)(combined different variables)	STN (--)(representing soil texture)	MC (%) soil moisture content)	DD (kN) Calculated using ASABE form by the modified Fi parameter)
0.019	0.042	6.31	3.49	6.15	6.55
0.075	0.105	7.34	16.47	11.00	11.92
0.036	0.105	7.34	23.68	15.90	14.87
0.152	0.105	7.34	7.69	5.54	5.07
0.073	0.105	7.34	11.05	8.33	8.47
0.095	0.105	7.34	8.32	6.56	6.19
0.046	0.105	7.34	11.96	9.60	9.51
0.031	0.105	7.34	13.08	10.58	10.80
0.050	0.105	7.34	9.88	8.01	7.96
0.065	0.105	7.34	9.10	7.41	7.04
0.024	0.105	7.34	14.20	11.92	11.91
0.108	0.457	8.26	19.55	16.30	16.50
0.053	0.457	8.26	13.67	15.41	15.35
0.065	0.042	11.58	1.87	3.25	3.51
0.126	0.030	13.82	10.45	16.67	16.54
0.074	0.030	13.82	10.99	18.15	18.66
0.058	0.030	13.82	11.51	19.06	19.15
0.463	0.596	14.69	3.14	2.19	2.71
2.232	0.596	14.69	1.72	1.30	0.95
0.277	0.596	14.69	4.06	3.15	3.58
1.339	0.596	14.69	1.84	1.62	1.61
2.328	0.596	14.69	0.42	0.38	0.63

Point #5

What is the economical - cost/environmental benefit of this modification?

Response to Point #5

Dear reviewer,

Thank you so much for your positive and valuable comments.

The high price of measuring devices and field experiments to acquire draft data od a tillage implement can support to develop a model to estimate such data .The deployment of these models will facilitate an overall reduction of data collection costs and the optimization of the affecting variables.

As the famous empirical model for draft force estimation is the ASABE form, which can be used in simulation purposes to determine the energy requirements or fuel consumption of farm implements. The economical - cost/environmental benefit of this research relies on different issues:

*The farm machinery engineers can use the ASABE form directly to estimate the draft requirements for tillage implements by replacing Fi parameter with the new Fi parameter developed in this research paper as the new Fi parameter for soil texture is now measurable”.

* The equations presented in the paper cam be formulated by any of computer language to make simulation program to predict the draft requirements of some tillage implements.

* By predicting the draft force in accurate manure, the fuel consumption of a tillage implement can be estimated.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report (New Reviewer)

Nil

Reviewer 3 Report (New Reviewer)

The authors satisfactorily answered my comments on the manuscript 'Modification of Values for the Horizontal Force of Tillage Implements Estimated from the ASABE Form using an Artificial Neural Network' which I raised in the 1st round.

Dear Editor,

The level of English is fine.

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.

Round 1

Reviewer 1 Report

Unfortunately, the manuscript submitted for review has serious flaws. The research was not conducted correctly, both in terms of field experiments and the creation of the ANN model.

That's why I also think it should be rejected.

Detailed comments are included in the pdf file.

Comments for author File: Comments.pdf

Author Response

General point

Comments and Suggestions for Authors

Unfortunately, the manuscript submitted for review has serious flaws. The research was not conducted correctly, both in terms of field experiments and the creation of the ANN model.

That's why I also think it should be rejected.

Detailed comments are included in the pdf file.

peer-review-27859236.v2.pdf

Response on the general point

Thank you for spending time providing quiet useful comments on our work. The under review manuscript had no serious flaws and the research was conducted correctly, both in terms of field experiments and the creation of the ANN model due to the following reasons:

In General, the research was conducted to overcome the disadvantages of applying the draft of tillage implements form published by American Society of Agricultural Biological Engineers (ASABE) as mentioned in the literatures. However, the ASABE form relies on information on soil texture through its soil texture adjustment parameter, which called (Fi) and it is not measurable, the geometry of the tool through the machine parameter values, which are not measurable, and tillage speed, tool width, and tillage depth which are measurable. To modify draft values of tillage implements estimated from the ASABE form, we need data related to the subject to make an artificial neural network (ANN) model in general form. However, the ANN model was created based on field data to determine the draft force of tillage implements like chisel, disk and moldboard plows. The required data were collected in the present research from field experiments and from previous sources, which also were run in the field.

In our field experiment, we used a chisel plow hitched to an agricultural tractor and pulled by another one, to run plowing experiments to gather data. The soil moisture content, soil bulk density and draft force of the chisel plow were measured according to standard methods and the investigated parameters levels for each run were appeared in Table (1), however the field experiment was run in three different locations to get variations in soil texture, soil moisture content, and soil bulk density. The total data points from our field experiments were 70 points. The data points from and the previous sources, which also were run in the field were 307 points. However, the whole data were statically describing by values of mean. minimum, maximum, and standard deviation and appeared in Table (2). We did not process the effect of investigated parameters levels in our field tillage experiments as this was not our aim. The purpose was only to gather related data for modeling, thus the experiment was conducted correctly.

The creation of the ANN model in our manuscript was created correctly due to the following reasons:

The ANN was comprised using three layers input, hidden, and output. In the input layer we inserted four parameters representing the most variables related to tillage operation (tractor power, initial soil bulk density, tillage depth, tillage speed, plow width, initial soil moisture content, sand percentage, clay percentage, silt percentage). To reduce some variables (tractor power, initial soil bulk density, tillage depth, tillage speed, and plow width), we created the first input parameter in the ANN model called a Working Field Criterion (WFC). This this was developed by the authors combining 5 variables as described in Eq. No. 6. The purpose was to reduce in input variables in the developed ANN model. Also, we used the soil texture norm (STN, dimensionless) as second input parameter in the ANN model, this norm combined all the soil contents of sand, silt and clay, as defined by Oskoui and Harvey [56], Eq. (4). The purpose was to reduce the input variables which represented soil texture from 3 variables (sand percentage, clay percentage, silt percentage) to 1 variable (STN) in the developed ANN model. Furthermore, we developed a regression model to formulate soil texture adjustment parameter, which called (Fi) in ASABE form to be measured from the soil contents of sand percentage, clay percentage, silt percentage as appeared in Eq. 5. Then the draft force was re determined using ASABE form using the New Fi model and the outcome (DD, the horizontal force estimated from equation using new-Fi parameter) was represented the third input parameter in the ANN model. However, the fourth parameter in the ANN model was initial soil moisture content. The research steps to obtain variables were appeared in the text. We created ANN model using backpropagation training method and trial and error method was applied to get the best ANN structure.

Comment 1

The purpose of the Authors' research was (lines 138-141): to develop a regression model to predict soil texture adjustment parameter (Fi) used in ASABE form [15] and to develop an ANN model to modify values of draft force of tillage implements estimated from the form of ASABE [15] based on wide range of working variables in the case of creating models using Artificial Neural Networks (ANN), the condition for obtaining valuable results is a large amount of valuable data. The Authors used two data sources (lines 153-154): The main source was from actual tillage field experiments using a chisel plow and (lines 183- The other source of the required data directly related to our study was from previous available literatures A summary of the results of the Authors' experiments regarding the chisel plow is included in Table 1. Unfortunately, there is no such summary for data taken from the publications of other authors. It is not explicitly stated how much data comes from the experiments.

Response on Comment 1

Thank you for spending time providing quiet useful comments on our work.

in Table (1), however the field experiment was run in three different locations to get variations in soil texture, soil moisture content, and soil bulk density. The total data points from our field experiments were 70 points. The data points from and the previous sources, which also were run in the field were 307 points. However, the whole data were statically describing by values of mean. minimum, maximum, and standard deviation and appeared in Table (2). We did not process the effect of investigated parameters levels in our field tillage experiments as this was not our aim. The purpose was only to gather related data for modeling, thus the experiment was conducted correctly.

Comment 2

Based on experimental data, the Authors calculated (using equations found in publications) WFC (working field criterion), STN (soil texture norm), DD (horizontal force estimated from equation using new-Fi parameter). The normalized values of WFC, STN, DD and MC (initial soil moisture content) were the inputs to the ANN of the MLP type. The output of the ANN was normalized modified horizontal force (FF). I have serious doubts about the research methodology planned by the Authors. Why use a neural network to calculate parameter values that appear in literature equations - ANN is unnecessary for this. The more so that using the same equations they calculate the data values, on the basis of which they create a neural model. In my opinion, the modeling process carried out in this way is wrong and therefore the manuscript is not suitable for publication.

Response on Comment 2

Thank you for spending time providing quiet useful comments on our work.

The research methodology planned by the authors were appeared in the research steps to obtain variables in the text. We created ANN model using backpropagation training method and trial and error method was applied to get the best ANN structure. The modeling using multiple linear regression is dependent on the linear relationships among variables but ANN algorithm can deal the nonlinear relationships among variables. The ANN in our manuscript was not used to calculate parameter values that appear in literature equations, but it used to create an ANN model to get the modify draft values of tillage implements estimated from the ASABE form to overcome the form disadavanges, thus ANN is necessary for this to overcome the nonlinear relationships among variables. The ANN modeling process carried out in this manuscript was depended on four different inputs which represented the most working conditions in tillage operation and trial and error method was applied to get the best ANN structure.

Comment 3

Doubts are also raised by the methodology of the experimental research conducted by the Authors. They used two tractors (lines 166-169), of which The first tractor (tractor in the foreground) was used to deliver energy for pulling the chisel plow on the soil. The second tractor (the tractor at the rear of the test-path) was utilized for mounting the chisel plow via a tractor three-point linkage. The force meter (hydraulic dynamometer) was linked to the pulling tractor using a horizontal steel cable and mounted between the two tractors. Thus, the sum of the rolling force of the second tractor and the soil resistance force of the implement was measured. If so, this is a serious methodological error.

Response on Comment 3

Thank you for spending time providing quiet useful comments on our work.

We wrote” Two agricultural tractors were used in the tillage experiments for measuring the horizontal force (draft), as described in [35-40]. The first tractor (tractor in the foreground) was used to deliver energy for pulling the chisel plow on the soil. The second tractor (the tractor at the rear of the test-path) was utilized for mounting the chisel plow via a tractor three-point linkage. The force meter (hydraulic dynamometer) was linked to the pulling tractor using a horizontal steel cable and mounted between the two tractors. We did not write ”Thus, the sum of the rolling force of the second tractor and the soil resistance force of the implement was measured. If so, this is a serious methodological error”. The draft force was determined in this research as mentioned in [35-40] by subtract the two forces, the first was rolling resistance as force value from the whole unite i.e. two tractors + the chisel plow , however, the chisel plow was raised and the second force was draft force required to pull the whole unit with the chisel plow inside the soil. Thus there was no a serious methodological error.

Comment 4

The Authors state that (lines 143-144): Such an explanation is superfluous. ANNs are a method used for modeling for several dozen years and the information about the basics of ANN operation, which was included in the work, is superfluous.

Response on Comment 4

Thank you for spending time providing quiet useful comments on our work.

We gave little information about ANN in the text to show the basics of ANN operation. We delated (lines 143-144) “Thus, this study’s key contribution is explaining the principles of ANN technique and its applicability in draft prediction for tillage for better farm machinery management”

Reviewer 2 Report

1. The "2.7 The required equation for developing the Excel spreadsheet" should be rewritten as science description.

2. The "Excel spreadsheet" seems not important in the study if only calculation with the output from ANN and simple calculation. (Line 376-382, Line 145-149 and abstract)

3. Figure7, the context of Figure 7 has no reasonable explanation, such as Fvalue?, FF-value?. "Part of sceen capture" ?? . What is the all results?
Do not use a capture of screen in paper.

Author Response

Point 1

The "2.7 The required equation for developing the Excel spreadsheet" should be rewritten as science description.

Response 1

Thank you for spending time providing quiet useful comments on our work.

The "2.7 The required equations for developing the Excel spreadsheet" were rewritten as science description.

Point 2

The "Excel spreadsheet" seems not important in the study if only calculation with the output from ANN and simple calculation. (Line 376-382, Line 145-149 and abstract)

Response 2

Thank you for spending time providing quiet useful comments on our work. We delated the Figure (7) for Excel spreadsheet.

Point 3

Figure7, the context of Figure 7 has no reasonable explanation, such as F value?, FF-value?. "Part of screen capture" ?? . What is the all results?
Do not use a capture of screen in paper.

Response 3

Thank you for spending time providing quiet useful comments on our work. We delated the Figure (7) for Excel spreadsheet.

Reviewer 3 Report

I have a few comments:

Line 66, what means “e”?

Line 69, check the numbers K1 and K2.

Page 7. How you define parameters A, B, C?

Line 201, check cm3.

Line 306, reduce the number of parentheses in the equation (21)

How you calculated Standard error in Table 4

Are there units of measurement in the table 5?

You mentioned in the abstract and on line 382 that „a good prediction of the required horizontal force with an error of 10% was avhived.” Could you show how you got it?

Author Response

Point 1

Line 66, what means “e”?

Response Point 1

Thank you for spending time providing quiet useful comments on our work. We delated the “e”

Line 69, check the numbers K1 and K2.

Response Point 2

Thank you for spending time providing quiet useful comments on our work. We reviewed the paper again and the K1 and K2 values were 1.735 and 1618, respectively. You can seehttps://www.sciencedirect.com/science/article/pii/S1881836616301471

Point 3

Page 7. How you define parameters A, B, C?

Response Point 3

Thank you for spending time providing quiet useful comments on our work. Parameters A, B, C were defined in ASABE as they are machine parameters as follows: The constant parameter A is a function of soil strength, while the coefficients of B or C are related to tillage speed and they refer to the influence of working speed on horizontal.

Point 4

Line 201, check cm3.

Response Point 4

Thank you for spending time providing quiet useful comments on our work. Cm3 corrected to cm³

Point 5

Line 306, reduce the number of parentheses in the equation (21)

Response Point 5

Thank you for spending time providing quiet useful comments on our work.

the number of open parentheses in the equation (21) is three and the number of closed parentheses in the equation (21) is also three

Point 6

How you calculated Standard error in Table 4

Response Point 6

We extracted Standard error from excel spreadsheet

Point 7

Are there units of measurement in the table 5?

Response Point 7

Thank you for spending time providing quiet useful comments on our work.

Point 8

You mentioned in the abstract and on line 382 that „a good prediction of the required horizontal force with an error of 10% was achieved.” Could you show how you got it?.

Response Point 8

The sentence was modified to a percentage error of 10% was achieved. We added eq. 23 to show how we calculated percentage error

Round 2

Reviewer 1 Report

The Authors made only minor revisions to the manuscript. My comments from the previous research round are still valid. That is why I stand by my previous recommendation to reject the manuscript.

Author Response

Point 1

Does the introduction provide sufficient background and include all relevant references? Can be improved (x)

Response on point 1

Thank you for spending time providing quiet useful comments on our work.

We re-arranged the introduction and added sentences “A lot of research has been done on the subject of predicting the draft force needed by agricultural implements, and numerous methods for doing so have already been developed. The earliest technique was mathematical-analytical, and numerous mathematical models were created to forecast the draft force exerted by tillage tools [6].

The goal of Eq. (1) is to offer a preliminary prediction equation that can be used with a variety of soil conditions. The Eq. (1) gives a reasonable estimate of tillage implement draft but warns that within the same wide textural soil class, a range in draft of up to 50% can be anticipated [8].

However, to compensate for the shortcomings of using ASABE model [7] , researchers have developed and evaluate of intelligent computing methods such as artificial neural network models and fuzzy knowledge-based models, which have led to great progress in the application of many technologies and provides the possibility to solve complex agricultural engineering problems, in particular draft force prediction of agricultural implements [26-33]. After entering the relevant parameters for the implement, soil, and working conditions, these intelligent models could provide a straight estimate of the draft force of a tillage implement. To train these models, however, experimental values had to be acquired from a field experiment or a soil bin experiment. Additionally, the intelligent models did not take into account the connection between the draft force and input parameters intended to improve comprehension of the tillage process and mechanism [6]” to provide sufficient background and include all relevant references. Also we added the relevant references and deleted the unsuitable references.

Point 2

Are all the cited references relevant to the research? Can be improved (x)

Response on point 2

Thank you for spending time providing quiet useful comments on our work.

We removed the unsuitable references and we added the relevant references.

Al-Suhaibani, S.A. Use efficiency of farm machinery in Saudi Arabia. ASAE Paper No. 92-1044, 1992, ASAE, St. Joseph, Michigan, USA.
Jiang, X.; Tong, J. ; Ma, Y.; Sun J. Development and verification of a mathematical model for the specific resistance of a curved subsoiler. Biosystems Engineering 2020, 190, 107-119. https://doi.org/10.1016/j.biosystemseng.2019.12.004
McLaughlin,N.B.; Drury, C.F. ; Reynolds, W.D. ; Yang , X.M. ; Li, Y.X. ; Welacky, T.W. ; Stewart, G. Energy inputs for conservation and conventional primary tillage implements in a clay loam soil. Transaction ASABE 2008, 51,1153-1163.
Choi,Y.S.; Lee, K.S. ; Park, W.Y. . Application of a neural network to dynamic draft model. Agricultural and Biosystems Engineering2000, 1, 67-72.
Roul, A.K. ; Raheman, H. ; Pansare, M.S. ; Machavaram, R. . Predicting the draught requirement of tillage implements in sandy clay loam soil using an artificial neural network. Biosystems Engineering 2009,104, 476-485.
Marakoǧlu, T. ; Çarman, Fuzzy knowledge-based model for prediction of soil loosening and draft efficiency in tillage. Journal of Terramechanics 2010, 47,173-178.
Shafaei, S.M. ; Loghavi, M. ; Kamgar ,S. A comparative study between mathematical models and the ANN data mining technique in draft force prediction of disk plow implement in clay loam soil. Agricultural Engineering International: CIGR Journal, 20 (2018), pp. 71-79.
Askari, M. ; Abbaspour-Gilandeh, Y. Assessment of adaptive neuro-fuzzy inference system and response surface methodology approaches in draft force prediction of subsoiling tines. Soil and Tillage Research,2019, 194, p.104338

Point 3

Is the research design appropriate? Must be improved (x)

Response on point 3

Thank you for spending time providing quiet useful comments on our work.

Point 4

Are the methods adequately described? Must be improved (x)

Response on point 4

Thank you for spending time providing quiet useful comments on our work.

The creation of the ANN model in our manuscript was created correctly due to the following reasons:

The ANN was comprised using three layers input, hidden, and output. In the input layer we inserted four parameters representing the most variables related to tillage operation (tractor power, initial soil bulk density, tillage depth, tillage speed, plow width, initial soil moisture content, sand percentage, clay percentage, silt percentage). To reduce some variables (tractor power, initial soil bulk density, tillage depth, tillage speed, and plow width), we created the first input parameter in the ANN model called a Working Field Criterion (WFC). This this was developed by the authors combining 5 variables as described in Eq. No. 6. The purpose was to reduce in input variables in the developed ANN model. Also, we used the soil texture norm (STN, dimensionless) as second input parameter in the ANN model, this norm combined all the soil contents of sand, silt and clay, as defined by Oskoui and Harvey , Eq. (4). The purpose was to reduce the input variables which represented soil texture from 3 variables (sand percentage, clay percentage, silt percentage) to 1 variable (STN) in the developed ANN model. Furthermore, we developed a regression model to formulate soil texture adjustment parameter, which called (Fi) in ASABE form to be measured from the soil contents of sand percentage, clay percentage, silt percentage as appeared in Eq. 5. Then the draft force was re determined using ASABE form using the New Fi model and the outcome (DD, the horizontal force estimated from equation using new-Fi parameter) was represented the third input parameter in the ANN model. However, the fourth parameter in the ANN model was initial soil moisture content. The research steps to obtain variables were appeared in the text. We created ANN model using backpropagation training method and trial and error method was applied to get the best ANN structure.

Point 5

Are the results clearly presented? Can be improved( x)

Response on point 5

Thank you for spending time providing quiet useful comments on our work.

Under 3.3 section, we added “Unlike traditional statistical methods, the ANN approach is a data-based strategy. Therefore, prior understanding of the connections between the input factors is not necessary in this instance]. Additionally, non-linear ANN models can be used to infer relationships between input and output parameters that are more trustworthy and robust]. Although helpful, the published material does not cover all aspects of ANN theory and methodology. The ANN model used in this study was a feed-forward ANN type with a backpropagation algorithm for training purpose. It was established to estimate the modified values of the horizontal force based on four inputs: working field criterion, soil texture norm, initial soil moisture content, and horizontal force estimated by ASABE standard using the new -Fi – parameter. The established ANN model in this study used a dataset to train ANN configurations with various numbers of neurons in the hidden layer, number of epochs as well as various initial connection weights made up of neurons with various transfer functions. Thus, several epochs and neurons were evaluated by trial and error in order to find the best configuration of ANN for predicting the modified values of the horizontal force of some tillage implements .

The best ANN configuration should have less MAE, RMSE as well as high R² . The best ANN configuration from the network construction employed a single hidden layer, with twenty nodes . Table 6 provides more information on the characteristics of the best ANN architectures. For normalized data, the training error value was calculated to be 0.045099. For the training, test, and validation data sets, as shown in Table 6, our ANN demonstrated high values of R², as well as low values of RMSE and MAE. These outcomes demonstrate the high accuracy and great generalizability of our existing ANN for forecasting the modified horizontal force of tillage instruments. The RMSE, MAE, and R² for the best ANN configuration was 2.105 kN, 1.349 kN, and 0.8175, respectively for testing dataset (Table 6). In training, testing, and validation datasets, the performance of anticipated values of modified horizontal force is shown in Figures 3 through 5.

Point 6

Are the conclusions supported by the results? Must be improved ( x)

Response on point 6

Thank you for spending time providing quiet useful comments on our work.

We modify the conclusions to support the results

“ In this study, the Fi- parameter, which is not measurable and assumed to describe soil texture in the famous empirical model available by American Society of Agricultural Biological Engineers (ASABE) for horizontal force estimation of tillage implements was calibrated using a regression technique based on soil texture norm, which combined the sand, silt and clay contents of a soil with R²of 0.703. The purpose was to measure Fi parameter to modify the empirical model issued by ASABE to give accurate draft values of agricultural implements. Also, a set of variables—tractor power, plowing speed, initial bulk density, implement width, and tillage depth were formulated in one variable called working field criterion to represent working conditions. The relationships between the working field criterion, the soil texture norm, the initial soil moisture content, and the horizontal force estimated from the ASABE model based on the new Fi - parameter as independent variables, and the modified horizontal force as a dependent variable were accurately mathematically modeled by an ANN with configuration of 4-20-1. The results suggest the established ANN model as an operative tool that can be used for accurately predicting (R² value 0.8515, MAE value 2.155 kN, and RMSE value 2.523 kN) using validation dataset of the modified horizontal force of some tillage implements such as chisel, moldboard, and disk plows. The relative contribution of input variables was assessed using the established ANN model. Modified horizontal force was most significantly influenced by working field criteria and horizontal force as calculated by the ASABE standard using the new Fi - parameter, by 28.05% and 36.10%, respectively. It should be underlined that the selection of suitable parameters (tractor power, tillage depth, tillage speed, and implement width) are essential for effective tillage management for certain soil parameters such as texture, bulk density, and moisture content. Using the developed equations based on the extracted weights from the trained ANN model, an Excel spreadsheet was created. It can be used to manage the variables that will offer less draft force for tillage implements, while conducting tillage operation on a specific soil texture, as the user can change tractor power, tillage speed, tillage depth, implement width, soil bulk. Also, the developed Excel spreadsheet contributing a numerical method that can be used by agricultural engineers in the future”.

Reviewer 2 Report

Suggest figure 3 -5 are in the same size.