Prediction of ionospheric TEC by LSTM and OKSM during M class solar flares occurred during the year 2023

Abstract

Advancements in space weather forecasting have become crucial for understanding and mitigating the impacts of solar activity on Earth’s ionosphere. This research focuses on the prediction of Total Electron Content (TEC) during M-class solar flare events in 2023. TEC is a vital parameter for satellite communications and navigation, making accurate forecasting imperative. Two prediction models, Long Short-Term Memory (LSTM) neural networks and Surrogate Models based on Ordinary Kriging (OKSM), are employed. LSTM, known for capturing temporal dependencies, is contrasted with OKSM, a geostatistical interpolation technique capturing spatial autocorrelation. The study utilizes TEC measurements from the Hyderabad (HYDE) GPS station for model training and evaluation along with solar and geomagnetic parameters. The performance metrics for both models across various solar flare dates are measured using Root Mean Square Error (RMSE), Normalized RMSE, Correlation Coefficient (CC), and Symmetric Mean Absolute Percentage Error(sMAPE). The research interprets the results, highlighting the strengths and limitations of each model. Notable findings include LSTM’s proficiency in capturing temporal variations and OKSM’s unique spatial perspective. Different solar flare intensities are analyzed separately, demonstrating the model’s adaptability to varying space weather conditions. The average performance metrics during M 4.65 SF events for the OKSM model, in terms of Root Mean Square Error is 5.61, Normalized RMSE is 0.14, Correlation Coefficient is 0.9813, and Symmetric Mean Absolute Percentage Error is 14.90. Similarly, for LSTM, the corresponding averages are 10.03, 0.24, 0.9313, and 28.64. The research contributes valuable insights into the predictive capabilities of LSTM and OKSM for TEC during solar flare events. The outcomes aid in understanding the applicability of machine learning and geostatistical techniques in space weather prediction. As society’s reliance on technology susceptible to space weather effects grows, this research is pivotal for enhancing space weather forecasts and ensuring the robustness of critical technological infrastructure on Earth.