Next Article in Journal
D2Former: Dual-Domain Transformer for Change Detection in VHR Remote Sensing Images
Next Article in Special Issue
Assessing Urban Mobility Resilience: An Exploratory Approach Using Hazard-Based Duration Models
Previous Article in Journal
Enhancing Signal Recognition Accuracy in Delay-Based Optical Reservoir Computing: A Comparative Analysis of Training Algorithms
Previous Article in Special Issue
Study on Landslide Displacement Prediction Considering Inducement under Composite Model Optimization
 
 
Article
Peer-Review Record

Short-Term Flood Prediction Model Based on Pre-Training Enhancement

Electronics 2024, 13(11), 2203; https://doi.org/10.3390/electronics13112203
by Yang Xia * and Jiamin Lu
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Electronics 2024, 13(11), 2203; https://doi.org/10.3390/electronics13112203
Submission received: 6 May 2024 / Revised: 31 May 2024 / Accepted: 4 June 2024 / Published: 5 June 2024
(This article belongs to the Special Issue AI in Disaster, Crisis, and Emergency Management)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This paper proposed a Pre-training Enhanced Short-term flood prediction Model (PE-SFPM), which applies a random masking and prediction strategy to effectively mine historical trend information during pre-training stage, and leverages attention mechanisms for flood discharge prediction.

 

1) There are some grammatical errors in the paper. For example, Line 96, “basing on” is wrong. Please check the whole paper to improve the readability of the paper and ensure that the language accurately conveys the technical content without ambiguity.

2) The meaning of the symbols in some formulas and the formulas need to be interpreted, such as formulas (9), (11), (20), (22) and etc.

3) In the description of the proposed method, the two stages are described in detail, but the work of the whole network in not introduced, and the cost function and training flow of the network are not mentioned.

4) There is no description of the operating environment of the experiments.

5) The comparison methods are all before 2021, so it is recommended to compare with the latest method.

Comments on the Quality of English Language

 Moderate editing of English language required

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

See attached.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The paper describes a topic of great interest under climate change, namely a short-term flood prediction model.

Considering the impact of floods on life, the use of artificial intelligence tools for prediction is essential.

The paper is well structured and the research methodology is properly described. 

However, as the data used in the training is older than 10 years, we suggest identifying sources that allow the use of more recent information. This would allow training and testing of the data so that the presented model would be more useful for flood prediction. GIS is a widely used tool, so an update would be possible.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Thank the authors for addressing my questions and making revisions based on the problems I have pointed out. I suggest a minor revision before the publication of this manuscript.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Seems the authors did not address some of the critical points.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The paper in this form has content improvements.

Conclusions are still poorly described, a more detailed description would be useful.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Back to TopTop