Improving One-Day-Ahead Forecasting of Low-Latitude Amplitude Scintillation Using an Upsampling-Enhanced LSTM

Abstract

The scintillation in radio wave propagation, particularly in regions near the magnetic equator, is found to be introduced by the ionospheric irregularities causing unsatisfactory performance in satellite based applications. In order to mitigate this effect, we design a long short-term memory (LSTM) model to forecast amplitude scintillation at one-minute resolution. Additionally, the upsampling-based feature preprocessing is introduced to improve forecasting performance, especially for short-term severe scintillation events. In terms of R<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> which is a popular forecast evaluation metric, our proposed model exhibits about 20% improvement over the same LSTM model without upsampling. Furthermore, although existing studies achieve good forecasting accuracy up to 4 hours ahead, the proposed model sets a benchmark with one-day-ahead forecasting, but at the cost of longer training time due to upsampling.