Prediction of Global Ionospheric TEC Enhancement in response to Solar Flares

Earth ionosphere is highly dynamic and influenced by multiple factors, among which the solar flares induce significant variations in the total electron contents (TEC). Variations of solar flares, including soft X-rays, EUV, and FUV, strongly affect the spatiotemporal distribution of TEC on a global scale. Although numerous studies have examined the TEC response to solar flare, critical characteristics such as global distribution of TEC variations due to solar flare demand comprehensive statistical investigations. Furthermore, machine learning (ML) applications for global TEC prediction during solar flares remain limited and lack the incorporation of solar flare effect. We propose the use of advanced deep neural network to improve prediction and warning of TEC response during solar flares and mitigate their negative impact.