Estimation Model of Global Ionospheric Irregularities: An Artificial Intelligence Approach. Issue 9 (16th September 2022)

• Record Type: Journal Article
• Authors: Tian, Penghao; Yu, Bingkun; Ye, Hailun; Xue, Xianghui; Wu, Jianfei; Chen, Tingdi
• Is Part Of: Space weather. Volume 20:Issue 9(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-09-16
• Subjects: deep learning -- ionospheric irregularities -- S4max -- ionosphere -- sporadic E -- radio occultation; Space environment -- Periodicals; 551.509992
• DOI: 10.1029/2022SW003160
• Languages: English
• ISSNs: 1542-7390

Abstract

Abstract: The ionospheric sporadic E layer, the ionospheric irregularities of enhanced electron density, appears in the Earth's ionosphere at altitudes between 90 and 120 km, which supports the real‐world radio communication needs of many sectors reliant on ionosphere‐dependent decision‐making. The prediction of the occurrence of sporadic E layers has been extremely difficult due to the highly complex behavior. Conventional numerical methods are limited because of the inability to extract high‐level information from data. Deep learning is a powerful tool for mining latent features from data, which can theoretically avoid assumptions constraining physical methods. Inspired by feature extraction, we applied deep learning to explore latent relationships between mapping observable lower atmospheric data and ionospheric data from limited observations. The proposed model was trained with high‐resolution ERA5 data during 1 January 2007–30 August 2018 as input and corresponding ionospheric sporadic E data collected from COSMIC RO measurements as output. The results show that the model can learn complex relevance as bridges connecting the input and the desired output and obtain excellent performance and generalization capability by applying multiple evaluation criteria. Additionally, we established several model architecture training methods to explore the performance of the model with different input data. The statistic results show that model inference performance is proportional to the abundance of input information and is impacted by intraseasonal variability. The inference capability of the model achieves the best performance in the June–August (JJA) and December–February (DJF) seasons, which is the exact period of sporadic E layer significant occurrence, although different models are evaluated. Plain Language Summary: Deep learning has been shown to be an efficient technique in atmospheric sciences as well as weather and climate prediction applications, such as forecasting the occurrence of ionospheric irregularities, which is a challenging task because of their highly complex behavior. In this study, we present an image‐based artificial intelligence (AI) approach to estimate global ionospheric irregularity intensity by combining lower atmospheric information and satellite measurements. The trained deep learning model can correctly estimate the spatial structure and seasonal variation in ionospheric irregularities. Furthermore, the novel technique demonstrates that the accuracy of model inference is correlated with the amount of supplied atmospheric information. The inference ability of the model performs better in summer and winter due to significant ionospheric irregularities in such seasons according to statistical classification metrics. This inspiring model could provide support in advanced warning for space weather and satellite navigation communities. Key Points: An artificial intelligence model was proposed to extract the latent correlation between the lower atmosphere and ionospheric irregularities The model prediction performance depends on the abundance of input information, including the lower atmosphere and solar activity The intraseasonal variability is found to influence the predictive capability of the model by applying classification evaluation criteria