Next Article in Journal
Determination of Polycyclic Aromatic Hydrocarbons from Atmospheric Deposition in Malva sylvestris Leaves Using Gas Chromatography with Mass Spectrometry (GC-MS)
Next Article in Special Issue
Dispersion Modeling of Odor Emissions from Area Sources in a Municipal Wastewater Treatment Plant
Previous Article in Journal
Impact of Large-Scale Circulations on Ground-Level Ozone Variability over Eastern China
Previous Article in Special Issue
Characteristics of Volatile Organic Compounds Emissions and Odor Impact in the Pharmaceutical Industry
 
 
Article
Peer-Review Record

Innovative Approaches to Industrial Odour Monitoring: From Chemical Analysis to Predictive Models

Atmosphere 2024, 15(12), 1401; https://doi.org/10.3390/atmos15121401
by Claudia Franchina 1,2, Amedeo Manuel Cefalì 1,2,*, Martina Gianotti 1,2, Alessandro Frugis 3, Corrado Corradi 3, Giulio De Prosperis 3, Dario Ronzio 1, Luca Ferrero 2, Ezio Bolzacchini 2 and Domenico Cipriano 1
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3:
Atmosphere 2024, 15(12), 1401; https://doi.org/10.3390/atmos15121401
Submission received: 11 September 2024 / Revised: 15 November 2024 / Accepted: 15 November 2024 / Published: 21 November 2024
(This article belongs to the Special Issue Environmental Odour (2nd Edition))

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The authors have attempted an intersecting approach to address odor measurement and data interpretation. However, several shortcomings need to be addressed.

1. The authors highlight the reliability of the eNose in the abstract, but this aspect is not adequately covered in the discussion section of the manuscript. Please add text explaining the reliability of the measurements.

2. One of the aims of this study is to develop a method for converting chemical concentrations to odor units. Although several models have been proposed, the manuscript lacks details on how this approach can be applied in real-life situations. Please discuss how the approach developed in this study could be applied in practice.

3. Table 1 presents a correlation matrix. The authors should explain how this correlation matrix was developed in the Materials and Methods section.

4. Figure 4: The data presented in the figure is confusing. A box plot is recommended for this type of data.

5. Figure 5: The current plotting does not reveal much information. Adjusting the x-axis scale would help display the data more clearly.

6. Figures 6-9: While the authors aim to demonstrate correlations between different parameters, there is no clear correlation in most cases. These figures could be moved to the supplementary information section, given the large number of figures in the manuscript. The observations could be explained in the text.

7. The authors should explain the purpose of using the Random Forest algorithm, along with a list of predictive variables, which is currently missing.

8. Figure 11 is incorrectly labeled as Figure 1. Please correct this.

9. Tables 3-8: The authors should explain the significance of the key numbers and how they impact the accuracy of the predictions.

10. Tables 6-7: The model parameters are presented, but, as with any predictive model, it is important to show the confidence ranges for these parameters. Please add this information to the tables and explain how these ranges were determined in the Materials and Methods section.

11. Figures 16 and 17: Please include a description of the objective evaluation of prediction accuracy (currently only presented in the table).

12. Please add some discussion on the application of the machine learning approach used in the study.

13. The conclusion should focus more on the key outcomes of the study, including the major contributions to the field.

14. Please ensure that all notations used in the equations are clearly explained in the text.

15. Line 18 in the Abstract: Change “specific chemical sensor” to “specific chemical sensor readings.”

 

Comments on the Quality of English Language

The quality of English in general is very good. Some minor edits would be required.

Author Response

Dear, 

Thanks for the revisions made. Attached are the answers to your questions.
Best regards,
Claudia Franchina

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The paper is interesting. However, it has to be improved before publication.

1. There are several places with error of reference,such as line 406,408, 422 etc.

2. The figures are very blur, such as fig. 6-11, the resolution is low.

3. The paper mentioned three RF algorithms. However, no imformation about the RF algorithms. Please show us the important information.

4. For training the model, why choose 30-70%. I suggest 80-20% ratio between the test and the predictive model. 5-fold validation can be added.

5. the format of the reference needs to be improved.

Comments on the Quality of English Language

English is ok.

Author Response

Dear, 

Thanks for the revisions made. Attached are the answers to your questions.
Best regards,
Claudia Franchina

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

In my opinion, this article is excellent, but few mistakes have to corrected:

Section "Introduction is too long. Please, make it shorter.

Line 251: Paragraph can not be made of 1 sentence only.

Starting from line 406 and further there are too many "error! Reference source is not found." Can you correct that.

Author Response

Dear, 

Thanks for the revisions made. Attached are the answers to your questions.
Best regards,
Claudia Franchina

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Thank you for addressing the comments and suggestions. The quality of the manuscript has greatly improved after the revision. 

There is one small error in Table 6, which would need to be corrected. Please change "Conference ranges" to "Confidence ranges" in the header row.

Author Response

Thank you for the reviews received.
The error in Table 6 has been corrected.

Reviewer 2 Report

Comments and Suggestions for Authors

The paper has been improved and is ready to be published.

Author Response

Thank you for the reviews received.
Back to TopTop