Automatic SWMM Parameter Calibration Method Based on the Differential Evolution and Bayesian Optimization Algorithm
Round 1
Reviewer 1 Report
Dear Editor,
Water
The present study focuses on the Jinshazhou drainage subdistrict in Guangzhou City as the research area. Utilizing the open-source nature of SWMM, Python code is developed to modify and record the engineering input files (.inp) and result output files (.out) [18]. Regarding the precision of parameter calibration, the Differential Evolution algorithm (DE) and Bayesian optimization algorithm (BOA) are improved in the following two aspects. The global search capability of the DE algorithm is combined with the local search capability of the BOA algorithm to prevent parameters from being trapped in local optima during the calibration process, so the SWMM model parameters are calibrated with high precision. An adaptive weight allocation strategy is used; during the calibration process, the proportions of the DE algorithm and BOA algorithm are dynamically allocated by the equilibrium level between constraint conditions and objective function to enhance the efficiency and precision of model calibration. This study aims to explore a new approach to improve the accuracy of parameters in urban stormwater runoff models, which enhances the predictive capability of intelligent urban stormwater runoff models. The subject addressed is interesting and within the scope of the Water. Also, the novelty of the manuscript is acceptable. Nevertheless, some major revisions have been found. After carefully solving the following issues, the manuscript could be a possible publication.
Major revisions:
- The literature review is incomplete. The application of DE, BOA, and hybrid algorithms should be reviewed in other fields of water resource engineering problems. You can cite the following studies:
https://doi.org/10.1016/j.jhydrol.2019.01.062
https://doi.org/10.1080/0305215X.2020.1775825
https://doi.org/10.1080/0305215X.2020.1775825
- What is the time computation of DE-BOA and other investigated algorithms? The time computation results should be added to the results section.
- What are the selected parameters for optimization algorithms? How do you select the best parameters for DE-BOA?
- The results of the present study should be compared with previously conducted studies.
- The name of section 3 should be replaced with “Results and discussion”
- Please add the main quantities results to the conclusion.
- Please add the limitation of the present study to the conclusion.
Minor revisions:
- The quality of Figure 3 is low.
- Please add resource linkes for employed data and maps.
Considering the mentioned points, this study in the current version needs major revisions.
Minor editing of English language required
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
In the submitted manuscript, the authors applied an integrated approach combining differential evolution and Bayesian optimization algorithms to calibrate the Storm Water Management Model (SWMM). The models' accuracy was assessed using various performance evaluation indicators. The results indicated that the DE-BOA approach achieved the closest match with the observations, surpassing a Nash-Sutcliffe efficiency (NSE) of 0.90. My specific comments on the manuscript are outlined below:
1. Ensure uniform citation style throughout the text, aligning with the preferred style of the journal.
2. Along with the efforts devoted to accomplish this study, highlight the major contributions of the study as well as its novelties compared to the existing body of knowledge at the end of the Introduction.
3. It would be very informative if the catchments and conduits (provided in Fig. 5) superposed/overlayed with the aerial photo of the focalized region (provided in the right hand side of Fig. 3). In this way, one can easily understand how the catchments are divided.
4. Elaborate on the classification of rainfall events, distinguishing between moderate and heavy rains. Define the rainfall thresholds or intervals that categorize events as moderate.
5. Provide appropriate references for the parameter value ranges listed in Table 3. Additionally, clarify how sensitive parameters were identified.
6. Explain the methodology for determining hyperparameters in the DE-BOA technique. Specify whether a trial-and-error approach was used or if insights were drawn from relevant literature.
7. Incorporate a discussion section to analyze the obtained findings, offering insights and interpretations.
8. In the conclusion, emphasize the limitations of the study to provide a balanced overview of the research.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Review comments have been provided to Editors.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Dear Editor,
Atmosphere
This manuscript is previously been carefully evaluated. The current version of the manuscript is acceptable.
With kind regards,
Author Response
Dear Reviewer，
Thank you very much for your comments on the improvement of the quality of our manuscripts, and it is a great honor to have your approval of this work.
With kind regards,
All authors
Reviewer 2 Report
Thnaks for addressing my comments.
Author Response
Dear Reviewer，
Thank you very much for your comments on the improvement of the quality of our manuscripts, and it is a great honor to have your approval of this work.
With kind regards,
All authors
Reviewer 3 Report
Review comment has provided to Editors.
Author Response
Dear Reviewer，
Thank you very much for your comments on the improvement of the quality of our manuscripts.
With kind regards,
All authors
