Machine Learning-Based Short-Term GPS TEC Forecasting During High Solar Activity and Magnetic Storm Periods

Abstract

Precise ionospheric total electron content (TEC) is critical for many aerospace applications, and forecasting ionospheric TEC is of great significance to it. Besides, short-term prediction of TEC values fills the gap between the TEC product latency and the precision. The machine learning-based approaches are promising in solving the non-linear prediction issues, particularly suitable for short-term GPS TEC forecasting due to its complex temporal and spatial variation. In this paper, four different machine learning models, i.e., Artificial Neural Network (ANN), Long Short-Term Memory (LSTM) networks, Adaptive Neuro-Fuzzy Inference System based on Subtractive Clustering (ANFIS-SC), and Gradient Boosting Decision Tree (GBDT) are applied for forecasting ionospheric TEC in three IGS GNSS monitoring stations at the low-latitude region (16°S to 10°S). The performance of these approaches in extreme conditions is investigated, including the high solar activity and magnetic storm, which are the most challenging scenario for TEC prediction. The results show that the machine learning algorithms outperform the Global Ionospheric Map (GIM) prediction model. The prediction accuracy during the high solar activity period was improved from 37.93% to 49.28%. During the magnetic storm period, the prediction accuracy was improved from 28.16% to 67.39% . Among the machine learning algorithms, the GBDT model outperforms the rest three algorithms in ionosphere prediction scenarios, which improves the prediction accuracy by 5.6% and 12.7% than the rest three approaches on average during high solar activity (2012-2015) and magnetic storm periods respectively.

Forecast Global Ionospheric TEC: Apply Modified U‐Net on VISTA TEC Data Set

“…Recently, machine learning approaches are widely used in the TEC forecast. These approaches are promising in solving nonlinear prediction problems (Han et al., 2021) and therefore can predict TEC more accurately (e.g., L. Liu et al., 2020). Various models were developed for single‐station (e.g., Huang & Yuan, 2014; Huang et al., 2015; Tebabal et al., 2018), regional (Ferreira et al., 2017; Song et al., 2018; Tebabal et al., 2019; Xia et al., 2021), and global TEC forecast (Cesaroni et al., 2020; Chen et al., 2022; Lee et al., 2021; L. Liu et al., 2020, 2022; J. Tang et al., 2022; Xia, Liu, et al., 2022; Xia, Zhang, et al., 2022; Yang et al., 2022).…”

“…Recently, machine learning approaches are widely used in the TEC forecast. These approaches are promising in solving nonlinear prediction problems (Han et al, 2021) and therefore can predict TEC more accurately (e.g., L. Liu et al, 2020). Various models were developed for single-station (e.g.,…”

A High Accuracy Spatial Reconstruction Method Based on Surface Theory for Regional Ionospheric TEC Prediction

“…Commonly used spatial interpolation methods, such as the thin plate spline (TPS) interpolation (Krypiak‐Gregorczyk et al., 2017), Kriging interpolation (Harsha et al., 2020), and stepwise linear optimal estimation method (Chen et al., 2021) have shown good performance in reflecting the global or local spatial distribution characteristics of TEC. With the rapid development of artificial intelligence (AI), intelligent methods based on machine learning have been introduced into the modeling of TEC and significantly improved the model's accuracy (Han et al., 2022). Typical machine learning algorithms such as support vector regression (SVR) (Zhukov et al., 2018), nearest neighbor algorithm (Monte‐Moreno et al., 2022), and decision tree method (Natras et al., 2022) all show good performance in ionospheric TEC prediction, effectively improving the prediction accuracy of existing TEC maps, simplifying the prediction process, and reducing the amount of calculation.…”

An improved fuzzy controller on electromechanical nano-tweezers

“…However, machine learning-based methods can also be considered (Goharimanesh et al, 2020). The second challenging level after arranging the rules is to improve each of the inputs and outputs, which would be related to the form of fuzzy membership functions (Goharimanesh et al, 2014; Han et al, 2022). To improve the structure of membership functions, the Taguchi method has been used in this paper by reducing the number of independent experiments.…”