Evaluation of Machine Learning Algorithm on Drinking Water Quality for Better Sustainability

Round 1

Reviewer 1 Report

Dear authors,

This research paper describes the actual topic – Evaluation of Machine Learning Algorithm on Drinking Water Quality for Better Sustainability. In their article authors noticed that numerous pollutants are affecting the quality of drinking water. Thus, in this paper, many characteristics of water are considered for water quality prediction using machine learning algorithms. As well, authors notice, that automating environmental problems is essential for the accuracy of decisions, sustainable plans, and faster actions.

And I would like to share with authors some doubts and remarks too: it seems important to notice, that it would be needed to concentrate on the discussion of the study. Thus, when developing this section it would be needed to include to the debate more future oriented theoretical implications, thus accessing deeper discussion and concluding insights.

Author Response

Discussion modified. Additional details are added to deepen the analysis on the reasons SVM and KNN have better performance than other algorithms.

Reviewer 2 Report

few correction suggested in the file

Comments for author File: Comments.pdf

Author Response

1. The .csv file was added.
2. Some abbreviations were corrected.

Reviewer 3 Report

The study deployed ML algorithm in understanding the water quality for better sustainability. The topic is interesting, however, further enhancement is required to strengthen the manuscript for publication:

Please refer following comments:

Abstract is too weak. Authors are encouraged to mention novelty and need of the study. Brief findings may be included in abstract.

Introduction: Line 20 to 25 need support of recent reference. Provide more clarity on objective in this section.

What is the rationale behind splitting data into 80% and 20%

Provide comparative analysis of used ML algorithm for more understanding. 

Conclusion section is too weak. It lacks in addressing research questions. Enhance limitations and future research directions of the study.

 Add more papers from 2021 and 2022.

 

 

 

 

Author Response

1. Abstract was changed to include findings.
2. References were added to support information in lines 20 to 25.
3. Reference concerning the rationale being splitting percentages was also added.
4. In discussion, comparative analysis of why SVM and KNN perform better was deeply explained based on obtained results.
5. Conclusion was also modified upon the reviewer’s suggestion to address research question, limitations, and future work.
6. Additional papers were also added.