Development of Water Quality Analysis for Anomaly Detection and Correlation with Case Studies in Water Supply Systems

Response to Reviewer 1 Comments

1. Summary

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. [This is only a recommended summary. Please feel free to adjust it. We do suggest maintaining a neutral tone and thanking the reviewers for their contribution although the comments may be negative or off-target. If you disagree with the reviewer's comments please include any concerns you may have in the letter to the Academic Editor.]

2. Questions for General Evaluation

Reviewer’s Evaluation

Response and Revisions

Does the introduction provide sufficient background and include all relevant references?

Yes/Can be improved/Must be improved/Not applicable

[Please give your response if necessary. Or you can also give your corresponding response in the point-by-point response letter. The same as below]

Are all the cited references relevant to the research?

Yes/Can be improved/Must be improved/Not applicable

Is the research design appropriate?

Yes/Can be improved/Must be improved/Not applicable

Are the methods adequately described?

Yes/Can be improved/Must be improved/Not applicable

Are the results clearly presented?

Yes/Can be improved/Must be improved/Not applicable

Are the conclusions supported by the results?

Yes/Can be improved/Must be improved/Not applicable

3. Point-by-point response to Comments and Suggestions for Authors

Comments 1:

Detailed Description of DBSCAN:

a.       Explain why DBSCAN was chosen for anomaly detection. Highlight its advantages in handling noise and detecting clusters of arbitrary shapes, especially for real-time monitoring data.

b.       Provide a brief theoretical background or reference for DBSCAN, ensuring clarity for readers unfamiliar with the method.

Response 1:

Thank you for pointing this out. I/We agree with this comment. Therefore, I/we have already updated regarding the selection of the DBSCAN algorithm and its advantages in handling noise in section 2.4.

Comments 2:

Dataset details:

a.       Describe the real-time monitoring data used for the analysis. Include details like the source of the data (e.g., sensors, historical records); the size, type, and frequency of the data collected; and preprocessing steps (e.g., cleaning, normalization) applied to the data before analysis.

Response 2:

Thank you for pointing this out. Therefore, I/we have already updated regarding real-time monitoring data in section 2.1. In addition, preprocessing steps have been explained in Figure 2.

Comments 3:

Parameter tuning for DBSCAN:

a.       Specify how the key parameters of DBSCAN – epsilon (eps) and minimum point (minPts) – were chosen.

b.       Mention whether these values were determined experimentally, based on domain expertise, or using an optimization technique.

Response 3:

Thank you for highlighting this. Therefore, I/we already updated the manuscript regarding the key parameters of DBSCAN in line 119-123.

Comments 4:

Anomaly definition:

a.       Clearly define what constitutes an “anomaly” in the context of water supply systems.

b.       Discuss the threshold or criteria used to classify data points as anomalous.

Response 4:

I appreciate for bringing this to my attention. Therefore, “anomaly” meaning in the context of water supply systems have been updated in manuscript line 107.

Comments 5:

Real-time implementation:

a.       Describe how DBSCAN was implemented for real-time data.

b.       Mention the computational tools or framework used (e.g. Phyton, R, MATLAB) and any modification to adapt DBSCAN for real-time processing.

Response 5:

I appreciate the feedback on here. Therefore, all the data used for the research is real-time data taken from water supply systems monitoring stations in Daegu, South Korea as explained in the materials and methods sections. In addition, the computational tools used to process the data is R-4.4.2 for Windows and has been updated in line 91.

Comments 6:

Evaluation metrics:

a.       Discuss how the effectiveness of anomaly detection was evaluated. For example: Metrics like precision, recall, F1 score, or accuracy.

b.       Benchmark or comparison with other algorithms (e.g. K-Means, Isolation Forest).

Response 6:

I appreciate the observation on this matter. This research is currently focused on developing the application of machine learning for monitoring water quality in water supply systems, and its effectiveness has not yet been analyzed. Furthermore, at the onset of the calculation, alternative algorithms such as k-Means and Isolation Forest were considered. However, these could not be utilized due to the large scale of the data.

Comments 7:

Systems architecture:

a.       If applicable, provide an overview of the architecture or workflow for integrating DBSCAN into the water supply system’s monitoring pipeline.

Response 7:

Thank you for your insightful comment. While integrating DBSCAN into a real-time water supply monitoring pipeline is an important consideration, this study primarily focuses on the application of DBSCAN for anomaly detection in historical water quality data rather than its direct integration into an operational monitoring system. Future research could explore real-time implementation and system integration as a potential extension of this work.

Comments 8:

Limitations and assumptions:

a.       Highlighting any assumption made during the methodology (e.g., data continuity, sensor reliability).

b.       Discuss potential limitations of DBSCAN in this context, such as sensitivity to parameter settings or scalability challenges.

Response 8:

Thank you for pointing this out. Therefore, the limitations of DBSCAN in the context have been updated in manuscript line 123

Comments 9:

Include diagrams or flowcharts to visually explain the methodology and data processing pipeline.

Response 9:

Thank you for catching that. Therefore, the methodology is visually explained through the flowcharts presented in Figure 2.

4. Response to Comments on the Quality of English Language

Point 1:

5. Additional clarifications

[Here, mention any other clarifications you would like to provide to the journal editor/reviewer.]

Response to Reviewer 2 Comments

1. Summary

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. [This is only a recommended summary. Please feel free to adjust it. We do suggest maintaining a neutral tone and thanking the reviewers for their contribution although the comments may be negative or off-target. If you disagree with the reviewer's comments please include any concerns you may have in the letter to the Academic Editor.]

2. Questions for General Evaluation

Reviewer’s Evaluation

Response and Revisions

Does the introduction provide sufficient background and include all relevant references?

Yes/Can be improved/Must be improved/Not applicable

[Please give your response if necessary. Or you can also give your corresponding response in the point-by-point response letter. The same as below]

Are all the cited references relevant to the research?

Yes/Can be improved/Must be improved/Not applicable

Is the research design appropriate?

Yes/Can be improved/Must be improved/Not applicable

Are the methods adequately described?

Yes/Can be improved/Must be improved/Not applicable

Are the results clearly presented?

Yes/Can be improved/Must be improved/Not applicable

Are the conclusions supported by the results?

Yes/Can be improved/Must be improved/Not applicable

3. Point-by-point response to Comments and Suggestions for Authors

Comments 1:

The Introduction is too concise and the reference list is quite limited. I suggest expanding the literature review by discussing what has been done on the topic of anomaly detection in water supply systems. As an example, you can refer to the study:

Mazzoni et al. 2024 Detection and pre-localization of anomalous consumption events in water distribution networks through automated, pressure-based methodology. Water Resources and Industry. https://doi.org/10.1016/j.wri.2024.100255

Response 1:

Thank you for pointing this out. I/We agree with this comment. Therefore, the literature background in the introduction section has been updated.

Comments 2:

Research novelty is not adequately highlighted. Moreover, in the first sections (i.e. Abstract and Introduction), the authors do not provide details regarding the method adopted in the study to perform anomaly detection. Please, underline the novelty elements that the study is supposed to present and specify the method/technique adopted in the study.

Response 2:

Thank you for pointing this out. Therefore, , I/we have already updated the manuscript in line 283-285.

Comments 3:

Line 70: replace “The study aims to achieve objectives: […]” with “The study aims to: […]”.

Response 3:

Thank you for noticing and mentioning it. Therefore, I/we have already updated the manuscript in line 63.

Comments 4:

Lines 17-20: Paraphrasing this sentence that is not clear in the current form.

Response 4:

I appreciate for bringing this to my attention. Therefore, I/we have already paraphrased the manuscript in line 16-20.

Comments 5:

Line 86: Define the acronym EPA.

Response 5:

Thank you for pointing this out. Therefore, I/we have already added the acronym of EPA in line 80.

Comments 6:

Figure 1: Rewrite the caption. The subject is currently missing.

Response 6:

Thank you for noticing it. Therefore, I/we have already written the caption on Figure 1.

Comments 7:

Line 101: Introduce Eps and minPts as variables by following the journal’s instructions.

Response 7:

I appreciate the feedback on this. Therefore, I/we have already updated the manuscript regarding Eps and minPts in line 121-123.

Comments 8:

Provide a brief discussion on study limitations

Response 8:

Thank you for pointing this out. Therefore, I/we have already updated the manuscript regarding Eps and minPts in line 261-263.

4. Response to Comments on the Quality of English Language

Point 1:

English language has to be revised by a native speaker to improve manuscript readability.

English language has to be improved to more clearly express the research.

Response 1: Thank you for your valuable feedback. We acknowledge that the manuscript would benefit from further refinement in language and readability. To improve clarity and ensure a more polished presentation, we have carefully revised the manuscript for grammatical accuracy, coherence, and conciseness.

5. Additional clarifications

[Here, mention any other clarifications you would like to provide to the journal editor/reviewer.]

Response to Reviewer 1 Comments

1. Summary

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. [This is only a recommended summary. Please feel free to adjust it. We do suggest maintaining a neutral tone and thanking the reviewers for their contribution although the comments may be negative or off-target. If you disagree with the reviewer's comments please include any concerns you may have in the letter to the Academic Editor.]

2. Questions for General Evaluation

Reviewer’s Evaluation

Response and Revisions

Does the introduction provide sufficient background and include all relevant references?

Yes/Can be improved/Must be improved/Not applicable

[Please give your response if necessary. Or you can also give your corresponding response in the point-by-point response letter. The same as below]

Are all the cited references relevant to the research?

Yes/Can be improved/Must be improved/Not applicable

Is the research design appropriate?

Yes/Can be improved/Must be improved/Not applicable

Are the methods adequately described?

Yes/Can be improved/Must be improved/Not applicable

Are the results clearly presented?

Yes/Can be improved/Must be improved/Not applicable

Are the conclusions supported by the results?

Yes/Can be improved/Must be improved/Not applicable

3. Point-by-point response to Comments and Suggestions for Authors

Comments 1:

The idea is promising and very interesting, but there are a few things that I would add to make the paper really interesting.

If you are trying to identify anomalies you should have first a dataset with real anomalies inside so that you can train and check the model against the ground truth.

In this phase you will also test alternative algorithms and then decide which one is the most promising.

Once you have done that and you are sure that the model works as you expected, you can try running it on data where you don’t know exactly what is happening, like the one you in the paper.

Response 1:

Thank you for pointing this out. I/We agree with this comment. Therefore, I/we have already updated regarding the selection of the DBSCAN algorithm and its advantages in handling noise in section 2.4.

Comments 2:

Are the assumption mentioned in the discussion section verified? Did you check the link between cause-effects with accurate measurements and a protocol? I think this is needed.

Response 2:

Thank you for pointing this out. Therefore, I/we have already updated regarding real-time monitoring data. In addition, preprocessing steps have been explained in Figure 2.

Comments 3:

All the plots are in black and they are not easy to understand, I would use color to identify the different lines in the plot.

Response 3:

Thank you for pointing this out. Therefore, I/we have already updated figures in color.

Comments 4:

The quality of the picture is not high, please use high resolution pictures.

Response 4:

I appreciate for bringing this to my attention. Therefore, I/we have already increased the quality of pictures.

Comments 5:

Are the data and the code available to the public in order to replicate the analysis?

Response 5:

Thank you for your comment. At this time, the data and code used in this study are not publicly available due to confidentiality and data-sharing restrictions. The dataset was obtained from real-time water quality monitoring stations, and its release is subject to institutional and regulatory policies. However, we are open to discussing potential collaborations or sharing specific insights upon request, within the allowable limitations

Comments 6:

Line 39: repetition of “concern” tries a different word.

Response 6:

Thank you for noticing it. Therefore, I/we have already updated the manuscript in line 38.

Comments 7:

line 65-67: “Although current developments of water quality surveillance systems provide real-time monitoring main water quality parameters” not clear, paraphrase.

Response 7:

Thank you for pointing this out. I/We agree with this comment. Therefore, I/we have already updated the manuscript in line 58.

Comments 8:

Line 77: paraphrase “study located” to “study is located”.

Response 8:

Thank you for noticing it. Therefore, I/we have already updated the manuscript in line 71.

Comments 9:

Line 80: “located” repetition.

Response 9:

Thank you for noticing it. Therefore, I/we have already updated the manuscript in line 74.

Comments 10:

Line 86: “EPA” please define the acronym before use it.

Response 10:

Thank you for pointing this out. Therefore, I/we have already added the acronym of EPA in line 80.

Comments 11:

Line 89: is there also a correlation between parameters? Did you take it into account? Do you have reference for the statement on the relationship?

Response 11:

I appreciate the feedback on this. Therefore, key parameters were chosen based on previous study conducted.

Comments 12:

Line 95: DBSCAN please add a reference.

Response 12:

Thank you for pointing this out. I/We agree with this comment. Therefore, I/we have already updated regarding the reference of the DBSCAN algorithm in line 109-115.

Comments 13:

Line 100: what is the final value of the key parameters and the hyperparameters?

Response 13:

Thank you for highlighting this. Therefore, I/we already updated the manuscript regarding the key parameters of DBSCAN in line 121-123.

Comments 14:

Line 110: As you show in Figure 2, the STL is before DBSCAN, would it not be better to present the algorithms in the same order they appear in the model?

Response 14:

Thank you for noticing it. Therefore, I/we have already rearranged the order in the manuscript.

Comments 15:

Line 116: LOESS add reference.

Response 15:

Thank you for pointing this out. I/We agree with this comment. Therefore, I/we have already updated regarding the reference of the LOESS in line 96.

Comments 16:

Figure 2:

a.       What is the primary data? You did not mention the secondary data in the text.

b.       “STIL” or “STL”?

c.       Caption: paraphrase: “(STIL)method” to “(STL) method”.

Response 16:

Thank you for noticing it. Therefore, I/we have already updated the manuscript regarding primary and secondary data on materials and methods section and changed has been made on the caption.

Comments 17:

Line 135: I could not find any time series on Figure 2 as you mentioned in the text.

Response 17:

Thank you for noticing it. Therefore, I/we have already updated the manuscript in line 140.

Comments 18:

Line 160: I could not find Figure S1-S6

Response 18:

Thank you for noticing it. Therefore, I/we have already updated the manuscript.

Comments 19:

Line 135: I could not find any time series on Figure 2 as you mentioned in the text.

Response 19:

Thank you for noticing it. Therefore, I/we have already updated the manuscript.

Comments 20:

Figure 4: could you add units on the y-axis?

Response 20:

Thank you for noticing it. Therefore, the y-axis in Figure 4 is labeled as "value after normalization calculation".

Comments 21:

Line 188: in the text you refer to End Point 490, while in the caption you mentioned data are only from Inflow Point 461, please add the missing data and plots.

Response 21:

Thank you for noticing it. Therefore, I/we have already updated the manuscript in Figure 3 caption

Comments 22:

Line 241-244: not clear, please paraphrase.

Response 22:

Thank you for noticing it. Therefore, I/we have already paraphrased the manuscript in line 244-247.

Comments 23:

Line 244: did you check the correlation between Temperature and Conductivity? Did you take it into account in your model and analysis?

Response 23:

Thank you for noticing it. The correlation between temperature and conductivity has been thoroughly analyzed through a comprehensive literature review, as cited in the references.

4. Response to Comments on the Quality of English Language

Point 1:

Response 1: Thank you for your valuable feedback. We acknowledge that the manuscript would benefit from further refinement in language and readability. To improve clarity and ensure a more polished presentation, we have carefully revised the manuscript for grammatical accuracy, coherence, and conciseness.

5. Additional clarifications

[Here, mention any other clarifications you would like to provide to the journal editor/reviewer.]

Response to Reviewer 1 Comments

1. Summary

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. [This is only a recommended summary. Please feel free to adjust it. We do suggest maintaining a neutral tone and thanking the reviewers for their contribution although the comments may be negative or off-target. If you disagree with the reviewer's comments please include any concerns you may have in the letter to the Academic Editor.]

2. Questions for General Evaluation

Reviewer’s Evaluation

Response and Revisions

Does the introduction provide sufficient background and include all relevant references?

Yes/Can be improved/Must be improved/Not applicable

[Please give your response if necessary. Or you can also give your corresponding response in the point-by-point response letter. The same as below]

Are all the cited references relevant to the research?

Yes/Can be improved/Must be improved/Not applicable

Is the research design appropriate?

Yes/Can be improved/Must be improved/Not applicable

Are the methods adequately described?

Yes/Can be improved/Must be improved/Not applicable

Are the results clearly presented?

Yes/Can be improved/Must be improved/Not applicable

Are the conclusions supported by the results?

Yes/Can be improved/Must be improved/Not applicable

3. Point-by-point response to Comments and Suggestions for Authors

Comments 1:

Author(s) applied most of the comments that I provided.

Response 1:

Thank you for your valuable comments and suggestions. I/we appreciate your time and effort in reviewing our work. We have carefully considered and incorporated most of your feedback into the revised manuscript.

4. Response to Comments on the Quality of English Language

Point 1:

Author(s) applied most of the comments that I provided, so it is acceptable.

Response 1:

Thank you for your feedback. I/we appreciate your comments and are glad the revisions meet your expectations.

5. Additional clarifications

Response to Reviewer 1 Comments

1. Summary

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. [This is only a recommended summary. Please feel free to adjust it. We do suggest maintaining a neutral tone and thanking the reviewers for their contribution although the comments may be negative or off-target. If you disagree with the reviewer's comments please include any concerns you may have in the letter to the Academic Editor.]

2. Questions for General Evaluation

Reviewer’s Evaluation

Response and Revisions

Does the introduction provide sufficient background and include all relevant references?

Yes/Can be improved/Must be improved/Not applicable

[Please give your response if necessary. Or you can also give your corresponding response in the point-by-point response letter. The same as below]

Are all the cited references relevant to the research?

Yes/Can be improved/Must be improved/Not applicable

Is the research design appropriate?

Yes/Can be improved/Must be improved/Not applicable

Are the methods adequately described?

Yes/Can be improved/Must be improved/Not applicable

Are the results clearly presented?

Yes/Can be improved/Must be improved/Not applicable

Are the conclusions supported by the results?

Yes/Can be improved/Must be improved/Not applicable

3. Point-by-point response to Comments and Suggestions for Authors

Comments 1:

Author(s) applied most of the comments that I provided.

Response 1:

Thank you for your valuable comments and suggestions. I/we appreciate your time and effort in reviewing our work. We have carefully considered and incorporated most of your feedback into the revised manuscript.

4. Response to Comments on the Quality of English Language

Point 1:

Author(s) applied most of the comments that I provided, so it is acceptable.

Response 1:

Thank you for your feedback. I/we appreciate your comments and are glad the revisions meet your expectations.

5. Additional clarifications

Response to Reviewer 2 Comments

1. Summary

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. [This is only a recommended summary. Please feel free to adjust it. We do suggest maintaining a neutral tone and thanking the reviewers for their contribution although the comments may be negative or off-target. If you disagree with the reviewer's comments please include any concerns you may have in the letter to the Academic Editor.]

2. Questions for General Evaluation

Reviewer’s Evaluation

Response and Revisions

Does the introduction provide sufficient background and include all relevant references?

Yes/Can be improved/Must be improved/Not applicable

[Please give your response if necessary. Or you can also give your corresponding response in the point-by-point response letter. The same as below]

Are all the cited references relevant to the research?

Yes/Can be improved/Must be improved/Not applicable

Is the research design appropriate?

Yes/Can be improved/Must be improved/Not applicable

Are the methods adequately described?

Yes/Can be improved/Must be improved/Not applicable

Are the results clearly presented?

Yes/Can be improved/Must be improved/Not applicable

Are the conclusions supported by the results?

Yes/Can be improved/Must be improved/Not applicable

3. Point-by-point response to Comments and Suggestions for Authors

Comments 1:

My second main comment (reported below) was not seriously taken from the authors.

C2: The Introduction is too concise and the reference list is quite limited. I suggest expanding the literature review by discussing what has been done on the topic of anomaly detection in water supply systems.

Response 1: Thank you for pointing this out. I/We agree with this comment. Therefore, I/we have updated the manuscript in Introduction section.

4. Response to Comments on the Quality of English Language

Point 1:

English language can be improved to more clearly express the research.

Response 1:

Thank you for your feedback. We have carefully revised the manuscript to improve clarity and readability.

5. Additional clarifications

Response to Reviewer 3 Comments

1. Summary

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. [This is only a recommended summary. Please feel free to adjust it. We do suggest maintaining a neutral tone and thanking the reviewers for their contribution although the comments may be negative or off-target. If you disagree with the reviewer's comments please include any concerns you may have in the letter to the Academic Editor.]

2. Questions for General Evaluation

Reviewer’s Evaluation

Response and Revisions

Does the introduction provide sufficient background and include all relevant references?

Yes/Can be improved/Must be improved/Not applicable

[Please give your response if necessary. Or you can also give your corresponding response in the point-by-point response letter. The same as below]

Are all the cited references relevant to the research?

Yes/Can be improved/Must be improved/Not applicable

Is the research design appropriate?

Yes/Can be improved/Must be improved/Not applicable

Are the methods adequately described?

Yes/Can be improved/Must be improved/Not applicable

Are the results clearly presented?

Yes/Can be improved/Must be improved/Not applicable

Are the conclusions supported by the results?

Yes/Can be improved/Must be improved/Not applicable

3. Point-by-point response to Comments and Suggestions for Authors

Comments 1:

On the response 16 you wrote: “Thank you for noticing it. Therefore, I/we have already updated the manuscript regarding primary and secondary data on materials and methods section and changed has been made on the caption.” -> I could not find any references to primary data.

Response 1:

Thank you for pointing this out. The data used is secondary data taken from organization and is not a direct sampling of the research object. Therefore, I/we have already updated more explanation regarding secondary data itself.

Comments 2:

Thank you for noticing it. Therefore, the y-axis in Figure 4 is labeled as “value after normalization calculation.” -> I did not find the updated label on the revised paper.

Response 2:

Thank you for noticing it. I/we already updated the figure.