Accurate Prediction of Dissolved Oxygen in Perch Aquaculture Water by DE-GWO-SVR Hybrid Optimization Model
, Lintong Zhang 3, Bo Liu 4, Linjie Chen 3, Wenqing Zhang 3, Lihang Xie 3, Xinze Liu 3, Fangfang Qu 2,3,* and Renye Wu 1,*
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsIn this study, the authors proposes a cluster intelligent combination model to predict the DO content with the characteristics of nonlinear and non-smooth water quality data.
The topic proposed by the authors and the data obtained are very interesting and will certainly be of interest to readers of the Journal of Applied Sciences. The manuscript was prepared very well. The manuscript requires minor corrections. Some specific comments on this manuscript are listed below:
1. In the introduction, please emphasize the aims of the study more clearly, e.g. in bullet points, to make it more readable.
2. Line 167 - (26°20'N, 119°38'E) – please add a map with the location of sampling places (points 01, 02, 03...)
3. Please explain in Table 1 (line 186), in the line below sample point 04, there is a line with only dots, what does this mean? Did the authors conduct research in all 37 ponds? Please explain it in the text and correct it in table 1 if it is not fully understandable.
4. Table 1 (line 186) – what does sample point 371 mean? Shouldn't it be 37? In line 169, the authors state that the research covered 37 high-density fish ponds.
5. Line 425-426 – please add abbreviations so that it matches the data in Figure 3, e.g. total dissolved solids (TDS), etc.
Author Response
Response to Reviewer 1 Comments
Thank you very much for taking the time to review this manuscript. Please find the detailed responses below and the corresponding revisions/corrections highlighted/in track changes in the re-submitted files.
Comment 1："In the introduction, please emphasize the aim of the study more clearly, e.g. in bullet points, to make it more ready."
Answer：We have made modifications on line 159 of the text and marked it in red.
Comment 2：“Line 167 - (26°20'N, 119°38'E) – please add a map with the location of sampling places (points 01, 02, 03...).”
Answer：We have added the modified image in line 189 of the text and marked it in red.
Comment 3：“Please explain in Table 1 (line 186), in the line below sample point 04, there is a line with only dots, what does this mean? Did the authors conduct research in all 37 ponds? Please explain it in the text and correct it in table 1 if it is not fully understandable.”
Answer：The dotted line below 04 in Table 1 omits some of the experimental data collected. This article conducted experiments in 37 fish ponds and collected data.
Comment 4：“Table 1 (line 186) – what does sample point 371 mean? Shouldn't it be 37? In line 169, the authors state that the research covered 37 high-density fish ponds.”
Answer：This article effectively collected 371 sample data from 37 high-density aquaculture fish ponds. Among them, 37 refers to 37 fish ponds, and 371 refers to the dataset used in this article after removing unavailable data(For example, missing values).
Comment 5：“Line 425-426 – please add abbreviations so that it matches the data in Figure 3, e.g. total dissolved solids (TDS), etc.”
Answer：We have made modifications in line 444 of the text and marked it in red.
Reviewer 2 Report
Comments and Suggestions for AuthorsThis paper appears to focus on predicting dissolved oxygen (DO) concentration using the correlation between pH, temperature, conductivity, salinity, total dissolved solids (TDS), and DO. The purpose is to predict dissolved oxygen based on the relationships between easily measurable parameters. Dissolved oxygen itself is also easily measurable. The need for prediction arises when forecasting future dissolved oxygen concentrations. However, specific information about predictions for dissolved oxygen concentrations at a later time could not be found.
It is considered more important to examine the physical and chemical meaning between actual water quality than relying solely on machine learning to predict more accurate numbers.
Title ; I recommend to use just 'perch' instead of 'california perch'.
Line 40; I recommend to use USD for wider authors' understanding instead of yuan.
Figure 1; Web sercive? Web service?
Comments on the Quality of English Language
Minor editing is needed. Checking typo is needed.
Author Response
Response to Reviewer 2 Comments
Thank you very much for taking the time to review this manuscript. Please find the detailed responses below and the corresponding revisions/corrections highlighted/in track changes in the re-submitted files.
Comment 1：“This paper appears to focus on predicting dissolved oxygen (DO) concentration using the correlation between pH, temperature, conductivity, salinity, total dissolved solids (TDS), and DO. The purpose is to predict dissolved oxygen based on the relationships between easily measurable parameters. Dissolved oxygen itself is also easily measurable. The need for prediction arises when forecasting future dissolved oxygen concentrations. However, specific information about predictions for dissolved oxygen concentrations at a later time could not be found.”
Answer：This article mainly predicts the current dissolved oxygen content in water accurately based on other readily available parameters in the current water quality combined with machine learning algorithms. In actual aquaculture, dissolved oxygen needs to be detected at all times, and detection instruments are expensive and easily damaged, and dirt needs to be cleaned at regular intervals. Therefore, to solve the above series of problems, this article uses water quality parameters combined with intelligent algorithms and machine learning models to predict the dissolved oxygen content.
Comment 2：“It is considered more important to examine the physical and chemical meaning between actual water quality than relying solely on machine learning to predict more accurate numbers.”
Answer：Physical and chemical testing is certainly more accurate, but it is accompanied by long detection time and expensive detection instruments. After using machine learning methods, the dissolved oxygen content can be predicted using other more easily obtainable parameters in water quality, which greatly reduces the time and money required to obtain dissolved oxygen. At the same time, it can also solve the potential risks for farmers due to the inability to timely and accurately obtain dissolved oxygen data caused by equipment loss and damage.
Comment 3：“Title ; I recommend to use just 'perch' instead of 'california perch'. ”
Answer：We have modified the title in the text and marked it in red.
Comment 4：“Line 40; I recommend to use USD for wider authors' understanding instead of yuan.”
Answer：Due to the reference to yuan in other people's literature, there have been no changes in the citation of this article.
Comment 5：“Figure 1; Web sercive? Web service? ”
Answer：We have added the modified image on line 190 of the text and marked it in red.
Reviewer 3 Report
Comments and Suggestions for AuthorsThe manuscript, it is on very good scientific level presented and It can be an usefull instrument for farmers.
Author Response
Response to Reviewer 3 Comments
Thank you very much for taking the time to review this manuscript. Please find the detailed responses below and the corresponding revisions/corrections highlighted/in track changes in the re-submitted files.
Comment 1：“The manuscript, it is on very good scientific level presented and It can be an useful instrument for farmers.”
Answer：We greatly appreciate your affirmation of the work in this paper!
Round 2
Reviewer 2 Report
Comments and Suggestions for AuthorsI think that the authors provided reasonable responses to the issues I raised last time.
