A Meteorological Data-Driven eLoran Signal Propagation Delay Prediction Model: BP Neural Network Modeling for Long-Distance Scenarios

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The manuscript presents a valuable contribution to the field of eLoran signal propagation delay prediction, offering both theoretical insights and practical methodologies. Addressing the concerns outlined above would further strengthen the paper and make it more accessible to a broader audience. Some minor revisions are needed to meet publication standards. 
1.    Define all acronyms at first use (e.g., “ASF” in the second paragraph).
2.    Missing BPNN Implementation Details. In Section 4, only the basic principle of the BP neural network was represented. Especially, Figure 9 does not provide a detailed explanation. It’s better to give the corresponding relationships between each input, output, hidden parameter, and model, as well as specify the optimization methods to facilitate the reader’s understanding.
3.    In Section 4.1, Sufficient and diverse meteorological data, such as temperature, humidity, air pressure, wind speed, etc., were obtained. However, when training the neural network model, only part of the factors, such as temperature, humidity, and air pressure, were adopted, but other data were not considered for use. There is a question here. On the premise that the relevant data has been obtained, why not make full use of it and only adopt a part of it?
4.    The pictures in the full text should be revised and improved. The figures are not clear enough, and the characters within the pictures are too small. Vector graphics might be needed to enhance clarity.
5.    The titles of Figures 15 and 16 have formatting errors. The title and the main text are mixed.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Based on the measured data of enhanced Loran (eLoran) differential reference stations, this paper analyzes the relationship between the propagation delay of eLoran signals and meteorological factors，especially suitable for long-distance scenarios. A prediction model incorporating factors such as temperature, humidity, water vapor pressure，and a multi-factor prediction model are established using a BP neural network. The prediction accuracy of different models are discussed, providing a new method for predicting the propagation delay of eLoran.

 

1. As mentioned in the background, the high-precision ground-based timing system has 175 differential reference stations throughout the country. However, in the research on the influence of meteorological factors on propagation delay in long-distance scenarios, why only a few differential reference stations in Henan are selected instead of other stations?
2. There are many machine learning related methods, why in this study, only the BP neural network model is selected as the research object, and no other models are selected?
3. When the BP neural network model is used to model the propagation delay prediction model, the relevant issues of parameter selection are not explained in the article. Please supplement the basis and process of parameter selection in the article.
4. Why should you choose this spatial resolution for meteorological data in the article? Can you choose a higher resolution? Please include your reasons for choosing this resolution in the article.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf