Prediction of Aircraft Wake Vortices under Various Crosswind Velocities Based on Convolutional Neural Networks
Round 1
Reviewer 1 Report
The article lacks a clear introduction and background information. It is important to provide context for the readers to understand the significance of the research and the motivation behind it.
The format of the headings in the article needs to be consistent. Some headings are in sentence case, while others are in title case. Choose one format and apply it consistently throughout the article.
List the major contributions at the end of the introduction part.
The figure captions should be more descriptive and informative. They should provide a brief overview of what the figure represents.
Description of data samples / data is not sufficiently provided. can you list the number of features that has been used to develop the model
What are the existing methods that have been compared? Discuss the improvements made by comparing the existing methods.
Provide the limitations of the method / Network.
Provide the R2 (R squared) value of the method
State about highly correlated features with respect to target.
Proof reading is required
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The ANN based reduced order model is a powerful tool to enhance the computational efficiency, but ensure the computational accuracy at the same time. In this work, a reduced order model of CFD is proposed based on convolutional neural networks to predict the aircraft wake vortex under various crosswind velocities.
1) What is the value of inflow in the training set? It should be provided.
2) In the work, the distribution of the inflow is uniform. The varied inflow distribution should be considered.
3) Are Figure 9 and 10 the results of the training set or the testing set? You should compare the results of the testing set, not the training set.
4) In the introduction section, the recent progress of reduced order model based on ANN should be reviewed. The ANN based reduced order model has been widely used in CFD, Multiphysics coupling issue and many other areas to significantly enhance the computational efficiency and ensure the computational accuracy. Here are some examples which may useful. [1] Artificial neural network based correction for reduced order models in computational fluid mechanics; [2] A Reduced Order Model Based on ANN-POD Algorithm for Steady-State Neutronics and Thermal-Hydraulics Coupling Problem; [3] Optimizing the homogeneity and efficiency of a solid oxide electrolysis cell based on multiphysics simulation and data-driven surrogate model.
5) English should be improved significantly. Too many grammatical errors and typos, as well as paragraph format, are found to exist. Many of the statements do not carry technically sound meaning or interpretation. Please review the manuscript through professional editorial.
English should be improved significantly. Too many grammatical errors and typos, as well as paragraph format, are found to exist. Many of the statements do not carry technically sound meaning or interpretation. Please review the manuscript through professional editorial.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
1. The strengths of the study over previous work are not made clear. The novel contribution of the work is not immediately obvious.
2. The English language requires improvement throughout to improve the clarity of the contribution.
The English language needs improvement.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
I don't have any further comments
Proof reading is required
Reviewer 2 Report
No further comment
