An Atmosphere Data Driven Q Band Satellite Channel Model with Feature Selection

Lu Bai, Qian Xu, Ziwei Huang, Shangbin Wu, Spiros Ventouras, George Goussetis, Xiang Cheng

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
4 Downloads (Pure)

Abstract

This paper proposes a novel atmosphere data driven Q band satellite channel model using two artificial neural networks, i.e., multi-layer perceptron and long short-term memory (LSTM), to estimate real-time channel attenuation at Q band via a set of atmosphere parameters. Seven atmosphere parameters for modeling satellite channel attenuation are selected by the least absolute shrinkage and selection operator (LASSO) algorithm from fourteen commonly used atmosphere parameters. Simulation results demonstrate that the multi-layer perceptron-based atmosphere data driven Q band satellite channel model via those seven atmosphere parameters is more accurate and less complex than that via the fourteen atmosphere parameters. Meanwhile, the accuracy performance of multi-layer perceptron-based and LSTM-based atmosphere data driven Q band satellite channel models, such as absolute errors and mean squared errors (MSEs), are discussed and analyzed. The complexity of multi-layer perceptron and LSTM in this model, such as training time, loading time, and estimation time, are also investigated. It can be seen that the estimated channel attenuation can well align with the measured channel attenuation.

Original languageEnglish
JournalIEEE Transactions on Antennas and Propagation
DOIs
Publication statusE-pub ahead of print - 28 Dec 2021

Keywords

  • Atmospheric measurements
  • Atmospheric modeling
  • Attenuation
  • Attenuation measurement
  • Channel models
  • data driven
  • feature selection
  • key atmosphere parameters
  • Q band
  • Satellite broadcasting
  • Satellite communication channel attenuation
  • Satellites

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'An Atmosphere Data Driven Q Band Satellite Channel Model with Feature Selection'. Together they form a unique fingerprint.

Cite this