Multilayer Perceptron Training Algorithms for Adaptive Learning of Gaseous Specific Attenuation Variables: A Performance Evaluation based on Mean Squared Error (MSE) Convergence
Keywords:
Neural networks, MLP training algorithms, MSE convergence, Atmospheric gaseous, Specific attenuationAbstract
The precise estimation of atmospheric gaseous attenuation is critical for the design of highfrequency satellite and terrestrial communication systems. The International Telecommunication Union (ITU-R) Recommendation P.676 provides a standardized model for calculating specific attenuation based on pressure, temperature, and water vapour density. However, the computational innefficiency of the line-by-line calculation often necessitates efficient surrogate modelling This paper evaluates the effectiveness of 13 distinct Multilayer perceptron (MLP) training algorithms for Artificial Neural Networks (ANNs) in approximating the ITU-R P.676 model as a function of water vapor density (rho) and temperature (T). We analyze the Mean Squared Error (MSE) convergence plots to determine and compare training performance and generalization capabilities , providing a benchmark for predictive atmospheric modelling.
Downloads
References
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published by Global Research Publication will be distributed under the terms and conditions of the Creative Commons Attribution 4.0 International License (CC-BY). So anyone is allowed to copy, distribute, and transmit the article on condition that the original article and source are correctly cited. Authors retain all copyright interest or it is retained by other copyright holders, as appropriate, and agree that the manuscript remains permanently open access in Global Research Publication's site under the terms of the Creative Commons Attribution 4.0 International License (CC-BY). Global Research Publication shall have the right to use and archive the content to create a record and may reformat or paraphrase to benefit the display of the record. For commercial use, we need to know about it.
