An Improved Neural-Network to Estimate the Inputs of Rino’s Ionospheric Scintillation Model

Ionospheric scintillation is a well-known effect that occurs when electromagnetic waves pass through the ionosphere, leading to rapid fluctuations in the phase and intensity of the received signal. In 1979 Charles Rino introduced a theory to compute the expected ionospheric scintillation. However, Rino's model requires knowing some input variables related to the physical properties of the ionosphere's plasma density irregularities. WBMOD model was especially developed to provide these parameters from climatological data as a function of several environmental conditions; however, the use of this model requires a license. In this study, using large datasets from past studies, a neural network has been trained to estimate the main output parameters from WBMOD: the probability density function of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$C_{k}L$</tex-math></inline-formula> and the value of the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$p$</tex-math></inline-formula>-slope (slope of power spectra of phase scintillation). This allows retrieving Rino's input variable to compute the scintillation indices <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$S_{4}$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sigma _\varphi$</tex-math></inline-formula>. The resulting software, called IonoSciNN, has been published as an open web application.