Next Article in Journal
Reflection Spectra Coupling Analysis and Polarized Modeling of Optically Active Particles in Lakes
Next Article in Special Issue
Ranking Sub-Watersheds for Flood Hazard Mapping: A Multi-Criteria Decision-Making Approach
Previous Article in Journal
Recirculating Water through Concrete Aggregates Rapidly Produced Ecologically Hazardous Water Quality
Previous Article in Special Issue
Performance of Machine Learning Techniques for Meteorological Drought Forecasting in the Wadi Mina Basin, Algeria
 
 
Article
Peer-Review Record

Runoff Prediction of Irrigated Paddy Areas in Southern China Based on EEMD-LSTM Model

Water 2023, 15(9), 1704; https://doi.org/10.3390/w15091704
by Shaozhe Huang 1, Lei Yu 2, Wenbing Luo 2,*, Hongzhong Pan 1, Yalong Li 2, Zhike Zou 2, Wenjuan Wang 3 and Jialong Chen 2
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3:
Reviewer 4: Anonymous
Water 2023, 15(9), 1704; https://doi.org/10.3390/w15091704
Submission received: 23 March 2023 / Revised: 17 April 2023 / Accepted: 22 April 2023 / Published: 27 April 2023

Round 1

Reviewer 1 Report

General Comment

The article shows a topic of great interest to the readership of the journal. However, some aspects should be modified before a possible acceptance of the manuscript for publication. Reviewer suggests major revision.

Detailed Comments

-          Introduction. Authors should highlight better the novelty of the study. What's new with respect to literature?

-          Introduction. The authors should improve the literature, considering the most recent studies (2022, 2023) on both topics and methodologies, e.g., LSTM-based models: 10.1016/j.jhydrol.2022.128431

-          In addition, it seems that the authors are proposing a hybrid approach, based on LSTM and EEMD, the advantages of the hybrid approach should be better emphasised.

-          Section 2. Authors are invited to provide more details on data used for the study (for examples a table with statistics on the considered variable, box plots representation, etc…)

-          Figure 5 is very hard to understand. The authors are encouraged to provide a second plot, below or above the existing graph, with absolute or relative errors for each model

-          Authors are encouraged to compute also different evaluation metrics like:

·        Mean Absolute Error (MAE)

·        Mean Absolute Percentage Error (MAPE)

·        Relative Absolute Error (RAE)

·        Mean Directional Accuracy (MDA)

For more details: 10.1016/j.agwat.2023.108232

-          Based on the conclusion section, what is further research direction.

 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Manuscript ID

water-2331660

Type

Article

Title

Runoff prediction of irrigated paddy areas in southern China based on EEMD-LSTM model

Authors

Shaozhe Huang , Lei Yu , Wenbing Luo * , Hongzhong Pan , Yalong Li , Zhike Zou , Wenjuan Wang , Jialong Chen

 

 

 

The manuscript concerns the important issue of the runoff prediction of irrigated paddy areas in southern China based on EEMD-LSTM model. To overcome the difficulty that the existing hydrological models cannot accurately simulate the hydrological processes with limited information in irrigated paddy areas in southern China, the paper presented a prediction model combining the Ensemble Empirical Mode Decomposition (EEMD) method and the Long Short-Term Memory network (LSTM). Meteorological factors were set as the multivariate input to the model. Rainfall, regarded as the main variable affecting runoff, was decomposed and reconstructed into a combination of new series with stronger regularity by using the EEMD and K-means algorithm. The LSTM was used to explore the data laws, then to simulate and predict the runoff of the irrigated paddy areas. The Yangshudang (YSD) watershed of the Zhanghe Irrigation System (ZIS) in Hubei Province, China was taken as the study area. Compared with the other models, the results showed that the EEMD-LSTM multivariate model had a better simulation performance, with NSE above 0.85. The prediction accuracy of peak flows was better than other models, as well as the performance of runoff prediction in rainfall and non-rainfall events. Overall, the EEMD-LSTM multi-variations model is suited for simulating and predicting the daily-scale rainfall-runoff process of irrigated paddy areas in southern China. It can provide technical support and help decision-making for efficient utilization and management of water resources. Suggestions and comments: As the value of IMF1 is very small does it significantly affect the accuracy of the prediction? What value of the R2 and NSE of the EEMD-LSTM and EEMD-LSTM models were both improved compared with the EEMD-LSTM model? The references should concerns the future paths for risk analysis in view of the possibility of a crisis situation, as presented in: A Hazard Assessment Method for Waterworks Systems Operating in Self-Government Units. Int. J. Environ. Res. Public Health 2019, 16, 767 (line 63). Where possible add doi number to publications. If possible indicate the future path for research, as it concerns really important issue.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

To overcome the difficulty that the existing hydrological models cannot accurately simulate the hydrological processes with limited information in irrigated paddy areas in southern China, this paper presented a prediction model combining the Ensemble Empirical Mode Decomposition (EEMD) method and the Long Short-Term Memory network (LSTM). The topic is interesting and within the scope of Water. I would recommend a Minor Revision.

(1)  How to combine LSTM and EEMD should be further illustrated.

(2)  More quantitative results should be highlighted in Abstract.

(3)  Table 2: The RMSE should have a unit.

(4)  The Figure 4 should be improved.

(5)  Tables 4-7: The RMSE should have a unit.

(6)  The uncertainty should be briefly discussed. The importance of hydrological prediction under climate change should be highlighted. The following references may be helpful.

https://doi.org/10.1038/s41893-022-01024-1

https://doi.org/10.1029/2019WR026065

https://doi.org/10.1007/s11269-017-1878-0

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 4 Report

  1. In line 31, it is not recommended to reference multiple files in one place. Please present the main contributions of these documents separately.
  2. In line 95, there are two "3." Please delete one.
  3. It is suggested that the innovation of the study be briefly described in the final part of the introduction.
  4. In Figure 2, under the Legend section, "Elevation m a.s.I" - what does " m a.s.I " stand for? Also, which book does the longitude and latitude grid represent?
  5. In Table 1, please provide the parameter units.
  6. In Table 4, what is the basis for selecting these three metrics for model comparison?
  7. Can the partially enlarged part of the image in Figure 4 and Figure 5 be clearer?
  8. Please explain your results first (which you have generally written) in relation to the wider literature and then compare and explain them with those of others' findings.
  9. In conclusion, it is recommended to explain the practical significance of the study.
  10. A proofreading by a native English speaker or proofreading service should be conducted to improve both language and organization quality.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

The manuscript has been improved, taking into account the suggestions of the Reviewers.

Reviewer 4 Report

The authors have answered all my questions adequately

Back to TopTop