Water Level Prediction Model Applying a Long Short-Term Memory (LSTM)–Gated Recurrent Unit (GRU) Method for Flood Prediction

Round 1

Reviewer 1 Report

The revised paper has addressed all my previous comments, and I suggest to ACCEPT the paper as it is now.

Author Response

Thank you for your valuable comments on this article. 

Reviewer 2 Report

Dear Editor

Paper can be published after addressing several minor issues:

1-All figures have a low resolution, they must be improved

2- Performance indicators must be the last section of methodology

3- What is the novelty of the paper?

4- what is the gap of research and what motivate the authors to do this research

5-how hyperparameters optimized for models

6- how inputs constructed? did author applied feature selection or did it manually? how?

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.

Round 1

Reviewer 1 Report

The Authors have applied some concepts of time series description - LSTM and GRU (which can be treated as some variation of the first one) - for predictionn of the possible flood. I don't see, what is the essential effect of their efforts nor how their calculations have been performed, because:

- if they have only applied a ready made (commercial?) models, applying LSTM and GRU , the text is completely worthless from the scientific point of view and has simply a form of their own professional (and technical only, not scientific) promotion - if so, could be possibly presented in come purely technical, not scientific, magazine;

- if they have prepared their individual and personal system (including the computer software), this element should be precisely described (as their original and scientific achievement)- if so, the paper must be completely rearranged and rewritten.

Reviewer 2 Report

 

1.     The manuscript presents water level prediction model applying long short-term memory and gated recurrent unit method for flood prediction, which is interesting. The subject addressed is within the scope of the journal.

2.     However, the manuscript, in its present form, contains several weaknesses. Appropriate revisions to the following points should be undertaken in order to justify recommendation for publication.

3.     Full names should be shown for all abbreviations in their first occurrence in texts. For example, LSTM in p.1, GRU in p.1, etc.

4.     For readers to quickly catch your contribution, it would be better to highlight major difficulties and challenges, and your original achievements to overcome them, in a clearer way in abstract and introduction.

5.     p.1 - long short-term memory and gated recurrent unit method are adopted for water level prediction. What are the other feasible alternatives? What are the advantages of adopting these soft computing techniques over others in this case? How will this affect the results? More details should be furnished.

6.     p.1 - meteorological data including upstream and downstream water level, temperature, humidity, and precipitation are adopted as input data. What are the other feasible alternatives? What are the advantages of adopting these parameters over others in this case? How will this affect the results? More details should be furnished.

7.     p.4 - historical records of 1988 to 2017 are taken. Why are more recent data not included in the study? Is there any difficulty in obtaining more recent data? Are there any changes to the situation in recent years? What are its effects on the result?

8.     p.4 - Yeojubo in Yeoju-si, Gyeonggi province is adopted as the case study. What are other feasible alternatives? What are the advantages of adopting this case study over others in this case? How will this affect the results? The authors should provide more details on this.

9.     p.10 - three performance comparison indicators are adopted to evaluate the model performance. What are the other feasible alternatives? What are the advantages of adopting these evaluation criteria over others in this case? How will this affect the results? More details should be furnished.

10.  p.10 - three model configurations are adopted in the experiments. What are the other feasible alternatives? What are the advantages of adopting these configurations over others in this case? How will this affect the results? More details should be furnished.

11.  p.10 - 9 models for 3 model structures and 3 datasets as shown in Table 2 are adopted in the experiments. What are the other feasible alternatives? What are the advantages of adopting these combinations over others in this case? How will this affect the results? More details should be furnished.

12.  p.11 - data from the past 20 hours are adopted as input data. What are other feasible alternatives? What are the advantages of adopting these input data over others in this case? How will this affect the results? The authors should provide more details on this.

13.  p.13 - “…It is judged that while the LSTM is lightweight, it has not been able to effectively learn high-dimensional data compared to the LSTM model.…” More justification should be furnished on this issue.

14.  p.16 - “…and it is judged that the GRU-based water level prediction model cannot learn effectively when the input data has many dimensions.…” More justification should be furnished on this issue.

15.  Some key parameters are not mentioned. The rationale on the choice of the particular set of parameters should be explained with more details. Have the authors experimented with other sets of values? What are the sensitivities of these parameters on the results?

16.  Some assumptions are stated in various sections. Justifications should be provided on these assumptions. Evaluation on how they will affect the results should be made.

17.  The discussion section in the present form is relatively weak and should be strengthened with more details and justifications.

18.  There are some occasional grammatical problems within the text. It may need the attention of someone fluent in English language to enhance the readability.

19.  Moreover, the manuscript could be substantially improved by relying and citing more on recent literature about contemporary real-life case studies of soft computing techniques on hydrologic prediction such as the following. Discussions about result comparison and/or incorporation of those concepts in your works are encouraged:

●          Fu, M.L., et al., “Deep Learning Data-Intelligence Model Based on Adjusted Forecasting Window Scale: Application in Daily Streamflow Simulation IEEE ACCESS 8: 32632-32651 2020.

●          Ebtehaj, I., et al., “Prediction of Daily Water Level Using New Hybridized GS-GMDH and ANFIS-FCM Models,” Engineering Applications of Computational Fluid Mechanics 15 (1): 1343-1361 2021.

●          Kaya, C.M., et al., “Predicting flood plain inundation for natural channels having no upstream gauged stations,” Journal of Water and Climate Change 10 (2): 360-372 2019.

20.  Some inconsistencies and minor errors that needed attention are:

●          Replace “…with various model structures and input data formats different…” with “…with various model structures and different input data formats…” in lines 16-17 of p.1

●          Replace “…Chapter 2 describes the…” with “…Section 2 describes the…” in line 112 of p.3

●          Some non-English characters appear in Figure 5 of p.6

●          Replace “…3.2. Model Struct…” with “…3.2. Model Structures…” in line 325 of p.11

●          Replace “…4.1. Train and validation result…” with “…4.1. Training and validation result…” in line 352 of p.12

●          Replace “…Mse was used as the…” with “…MSE was used as the…” in line 353 of p.12

●          Replace “…through Figure 11-13…” with “…through Figures 11-13…” in line 404 of p.14

●          Replace “…The test results also obtained similar results to model training and validation…” with “…The test results are similar to model training and validation results…” in line 416 of p.16

●          and more…

21.  In the conclusion section, some recommendations are made for further investigation. Why they are not performed in this study? More justifications should be furnished on this.

Reviewer 3 Report

 

 

1. Please, use spaces within Memory(LSTM) and Unit(GRU), in the title of the manuscript. The same should be done throughout the manuscript such as in abstract System(ASOS), keywords Memory(LSTM); Gated Recurrent Unit(GRU); etc. The use of brackets should be done by using space after a word and before the bracket, also within the figures.

2. Please within the abstract write down the explanation of the abbreviations LSTM and GRU.

3. Please, repost some of the main findings of your work within the abstract.

4. The authors should check if there is any copyright issue by using figure 1.

5. Please, provide new better analysis images for figure 2, figure 3, figure 8, figure 9, figure 11, figure 12, and figure 13.

6. Please remake the map in Figure 6. At this point is not readable. The legend should be bigger, the fonts should be a bit bigger as well. Also, a general map

7. Please separate the results-discussion sections. Each of them should be a separate section. Results should provide a concise and precise description of the experimental results, their interpretation, and the experimental conclusions that can be drawn. Discussion should provide the connection/review of your methodology to other works.

8. Please use passive voice within the manuscript.

9. Since you are using many abbreviations within your manuscript, please provide a table with all of them.