Modeling TEC Maps Over China Using Particle Swarm Optimization Neural Networks and Long‐Term Ground‐Based GPS, COSMIC, and Fengyun Data.

This paper presents a new model for ionospheric total electron content (TEC) over China. The new model is developed using a hybrid method composed of the particle swarm optimization (PSO) and artificial neural network and long‐term observations from 257 ground‐based global navigation satellite systems (GNSS) stations and space‐borne GNSS radio occultation systems (COSMIC and Fengyun) during the 14‐year period of 2008–2021. The PSO algorithm is used to optimize the traditional back‐propagation neural network (BP‐NN) model by reducing the effects of the local minimum problem. The new model is validated using out‐of‐sample data, and its results are compared to the BP‐NN, IRI‐2016 model, and global ionospheric maps provided by the International GNSS Service. Results show that TEC predicted from the new model agrees better with the reference TEC than the BP‐NN and IRI‐2016 models. The improvements made by the new model over the BP‐NN and IRI‐2016 models in the equinox, summer, and winter seasons of the solar maximum year (2015) are 4%–20%/20%–36%, 9%–21%/26%–42%, and 6%–22%/21%–43%, respectively, and their corresponding results in the solar minimum year (2019) are 12%–24%/41%–59%, 9%–24%/28%–56%, and 10%–26%/53%–72%. Furthermore, the new model well captures the diurnal evolution, seasonal variation, and variations in the ionospheric TEC under different solar activity levels. It also well captures the mid‐latitude summer nighttime anomaly over China, and the diurnal anomaly is more pronounced in the solar minimum year (2019) than in the solar maximum year (2015) in terms of the nighttime‐to‐noontime ratio and the range of months it lasts in a year. Plain Language Summary: With the continuous expansion of ground‐based and space‐borne global navigation satellite systems (GNSS) data sets, more and more high‐resolution, high‐accuracy, and long‐term measurements are available. These data can be used for characterizing, modeling, and forecasting the ionosphere. However, due to the limitation of data analysis tools and modeling techniques, only a fraction of the huge data set has been used. As proven by previous research, the back‐propagation neural network (BP‐NN) is an efficient approach in exploring hidden patterns from a large data set. Nevertheless, BP‐NN has shortcomings, for example, the possible local minimum and slow convergence rate problem. Therefore, this study uses the particle swarm optimization neural network and long‐term observations obtained from 257 ground‐based GNSS stations and space‐borne GNSS radio occultation systems (COSMIC and Fengyun) to develop a new model of ionospheric total electron content (TEC) over China. The new model captures the TEC diurnal evolution, seasonal variation, and variations under different solar activity levels. Moreover, the new model also well captures the mid‐latitude summer nighttime anomalies over China. This new model offers more opportunities for the investigation of large‐scale ionospheric phenomena over China, like the distribution of the mid‐latitude summer nighttime anomaly and its month‐to‐month variations. Key Points: A particle swarm optimization neural network based total electron content (TEC) model over China is developed using observations of ground‐based global positioning system, COSMIC, and Fengyun during 2008–2021The new TEC model performs better than the IRI‐2016 model and back‐propagation neural network model under high and low solar activity levelsMid‐latitude summer nighttime anomaly is well captured by the new model, and the diurnal anomaly is more pronounced in 2019 than in 2015 [ABSTRACT FROM AUTHOR]