A Novel Method for Gas Disaster Prevention during the Construction Period in Coal Penetration Tunnels—A Stepwise Prediction of Gas Concentration Based on the LSTM Method
, Ke Li 1,2,*, Fang Wang 1,2, Zonglong Zhang 1,2, Shuang Cai 2 and Liang Cheng 1,2,*
Round 1
Reviewer 1 Report
This study proposes a method for gas disaster prevention during the construction period in Coal penetration tunnel stepwise gas concentration prediction based on the LSTM method.
The aouthers did very will and I find this paper is a unique study on the subject and recommend it for publication.
Minor: In general, figures captions can be improved by describing what is a,b,c, etc (please see fig. 5)
Author Response
请参阅附件。
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Workplace safety is crucial for all employees because injuries can have significant losses to their families. Health and safety are critical factors in all industries and their branches, which also applies to mining complexes. Proposed preventive measures based on applying an adequate model will make the workplace more secure and safe for employees.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Dear Editor, The manuscript is well written. The title is interesting since there are many issues related to the gas disasters during the construction of the tunnel. But there are a few queries which the authors should address before this paper can be accepted for publication.
- Why is only 30 days of data selected? The 30 days of data is somehow limited to predicting the gas destruction for a longer period.
- During the different seasons, the behaviour and pressure of gas in the coal tunnel vary. Did they consider this aspect in the prediction model?
- In Table 2, the authors showed that the regressive coefficient value for all the prediction models is above 0.85%, which is unexceptional. Did they use a linear regression to predict the R2 value? I would like to see the crossplots for these predicted R2 values.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 4 Report
Dear Author
Originality and experimental sections are good. Article can be accepted for publication as it is
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 5 Report
1. The authors have reported a stepwise prediction method which is based on the optimal network prediction model for gas disaster prevention during the construction period of tunnel at the excavation workface.
2. I went through entire manuscript and found that the paper is logically arranged, abstract reflect the coverage of main thematic area chosen for the study. The introduction provides sufficient background and include all relevant references coverage of main thematic area chosen for the study. I am pleased to endorse the manuscript to be considered for publication in Sustainability.
3. However, similar kind of model was reported, long short-term memory recurrent neural networks trained and tested to CH4 leakage source in a chemical process module. Please justify and for reference see the article published.
· Selvaggio, André Zamith, Felipe Matheus Mota Sousa, Flávio Vasconcelos da Silva, and Sávio SV Vianna. "Application of long short-term memory recurrent neural networks for localisation of leak source using 3D computational fluid dynamics." Process Safety and Environmental Protection 159 (2022): 757-767.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 3 Report
All my comments are addressed.
Author Response
Please see the attachment.
