Artificial Neural Networks for Prediction of Rain Attenuation on Ku-band in South Africa

DOI

10.2991/978-94-6463-644-4_23How to use a DOI?

Keywords

Rain attenuation; Artificial Neural Network; Principal Component Analysis; Levenberg-Marquardt Algorithm

Abstract

In satellite communication networks on Ku-band and above, the propagation of signals is affected by various properties of weather conditions like hail, fog, and rain. The attenuation by rain is a dominant source of impairment of signal propagation operating on frequencies above 10 GHz. It is important to thoroughly investigate the possible rain-induced attenuation on Earth-satellite links so that appropriate mitigation measures can be enforced. This paper discusses the development of Principal Component Analysis-Artificial Neural Network (PCA-ANN) models for prediction of rain attenuation on satellite communication links for fixed satellite services. The proposed model was constructed using feed-forward back-propagation (FFBP) and cascade-forward back-propagation (CFBP) neural network types and their iterative performance was evaluated by Mean Square Error (MSE). This study was done using the 12-year database rainfall data measurements contacted by the South African Weather Service (SAWS) over Pretoria and Bloemfontein. The neural networks were trained using the first two Principal Components (PCs) to predict the rain attenuation that may be experienced in the network propagation links. The results of the proposed methodologies have been in comparison with the results obtained from the International Telecommunication Union-radio communication sector (ITU-R), Simple Attenuation Model (SAM), and Ajayi model. The proposed models show relatively low errors compared to the observed predicted attenuation.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Lekhetho Joseph Mpoporo
AU  - Pius Adewale Owolawi
AU  - Gbolahan Rilwan Aiyetoro
PY  - 2025
DA  - 2025/02/04
TI  - Artificial Neural Networks for Prediction of Rain Attenuation on Ku-band in South Africa
BT  - Proceedings of the 8th URSI-NG Annual Conference (URSI-NG 2024)
PB  - Atlantis Press
SP  - 232
EP  - 244
SN  - 2352-541X
UR  - https://doi.org/10.2991/978-94-6463-644-4_23
DO  - 10.2991/978-94-6463-644-4_23
ID  - Mpoporo2025
ER  -