Next Article in Journal
Inter-Comparison of Multiple Gridded Precipitation Datasets over Different Climates at Global Scale
Next Article in Special Issue
Multivariate Validation at Multistation of Distributed Watershed Hydrological Modeling Based on Multisource Data on Chinese Loess Plateau
Previous Article in Journal
Experimental Study on the Sloshing of a Rectangular Tank under Pitch Excitations
 
 
Article
Peer-Review Record

Monthly Runoff Prediction for Xijiang River via Gated Recurrent Unit, Discrete Wavelet Transform, and Variational Modal Decomposition

Water 2024, 16(11), 1552; https://doi.org/10.3390/w16111552
by Yuanyuan Yang *, Weiyan Li and Dengfeng Liu
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3:
Water 2024, 16(11), 1552; https://doi.org/10.3390/w16111552
Submission received: 11 April 2024 / Revised: 21 May 2024 / Accepted: 24 May 2024 / Published: 28 May 2024

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

 

Summary:

The article proposes a new methodology, DWT-VMD-GRU, for monthly runoff prediction, integrating discrete wavelet transform (DWT), variational modal decomposition (VMD), and gated recurrent unit (GRU) networks. The model's performance is compared against GRU, LSTM, DWT-GRU, and DWT-LSTM models using runoff and rainfall time series data.

 

Strengths:

1. Innovative Approach: The integration of DWT, VMD, and GRU networks offers a novel approach to monthly runoff prediction, potentially enhancing model accuracy.

2. Performance Improvement: The study demonstrates that the DWT-VMD-GRU model consistently outperforms alternative models across various evaluation metrics, indicating its effectiveness in capturing complex hydrological processes.

3. Methodological Insight: Identifying optimal sliding window durations for different input combinations provides valuable methodological insights for future research and application.

 

Weaknesses:

1. Data Limitations: Acknowledging the limitation of a relatively short dataset, particularly before 2005 at the Wuzhou station, the study needs to address concerns about the generalizability and robustness of the findings.

2. Scope Limitation: While the comparison with alternative models is comprehensive, the evaluation primarily focuses on runoff and rainfall data, potentially overlooking other influential factors affecting runoff prediction.

3. Future Research Directions: Although future research avenues are suggested, further elaboration on assessing model robustness, computational efficiency, and parameter sensitivity would strengthen the study's credibility and applicability.

 

Suggestions for Major Revision:

1. Data Augmentation or Extension: Consider augmenting the dataset through techniques such as data synthesis or incorporating data from additional hydrological stations to address concerns about dataset limitations.

2. Comprehensive Evaluation: Expand the scope of evaluation to include other relevant variables or external factors that may influence runoff prediction, providing a more holistic assessment of model performance.

3. Detailed Discussion: Elaborate on proposed future research directions, providing concrete plans for assessing model robustness, computational efficiency, and parameter sensitivity, thereby enhancing the study's completeness and potential impact.

 

Conclusion:

While the article presents a promising methodology for monthly runoff prediction, addressing concerns related to data limitations and expanding the scope of evaluation are crucial for ensuring the reliability and applicability of the proposed model. With major revisions focusing on data augmentation, comprehensive evaluation, and detailed discussion of future research directions, the study has the potential to significantly contribute to the field of hydrological forecasting.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Please check the attachment.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

No.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

Dear Authors,

The topic is interesting for the Journal covering river flow.  However a lot mathematical tools are used without physical background. In addition very few input data are used thus paper could be classified  as preliminary communication.

Specific comments

1)      The title should be improved e.g. "Monthly runoff prediction for Xijang River  in China based on neural network models”;

2)      It is not clear which physical variables are used as predictands (probably monthly precipitation sums)?;

3)      It is not clear status of mentioned river level;

4)      Time level of prediction is not clear, one month in advance or so?;

5)      If for runoff forecasting/prediction of precipitation sums is used on which way such forecasting/prediction of precipitation sums is done?.

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Accepted 

Reviewer 3 Report

Comments and Suggestions for Authors

I suggest paper to be published as it is.

Back to TopTop