ML Prediction of Global Ionospheric TEC Maps

Liu, Lei; Morton, Y. Jade; Liu, Yunxiang

doi:10.1029/2022sw003135

Cited by 19 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past decades, the rapid development of a wide range of ionospheric models, such as empirical models (Bilitza et al., 2017, 2022; Goncharenko et al., 2021), physics‐based models (e.g., Huba & Liu, 2020; McDonald et al., 2015; Richmond et al., 1992; Ridley et al., 2006; Schunk et al., 2002), data assimilation (DA) models (e.g., Chartier et al., 2021; Chen et al., 2016; Hsu et al., 2018; C. Y. Lin et al., 2017; Schunk et al., 2004; Sun et al., 2017), and machine learning models (e.g., L. Liu et al., 2022), has facilitated our understanding of the complex physical coupling processes of the magnetosphere/ionosphere/thermosphere/lower atmosphere system. The ultimate goal of these models is to better understand the near‐Earth space environment, mitigating the impacts of space weather on our daily life (e.g., Fang et al., 2022; Kataoka et al., 2022; Shultz, 2014).…”

Section: Introductionmentioning

confidence: 99%

Validation of Ionospheric Modeled TEC in the Equatorial Ionosphere During the 2013 March and 2021 November Geomagnetic Storms

et al. 2023

View full text Add to dashboard Cite

This paper presents the validation of modeled total electron content (TEC) from 14 ionospheric models, including empirical, physics‐based, and data assimilation (DA) models, hosted by the NASA/NSF Community Coordinated Modeling Center (CCMC), NOAA Space Weather Prediction Center, and NASA Jet Propulsion Laboratory (JPL). This study aims to assess the current progress and capability of the CCMC‐hosted ionospheric models in capturing the storm time ionosphere during the low and moderate solar flux years. We focus on the low‐latitude ionosphere (i.e., ±40° in magnetic latitude) and compare the modeled TEC with the Madrigal TEC during the 2013 March and 2021 November storms. Multiple metrics are used to quantitatively assess the models' accuracy, precision, association, bias, and capability in capturing the TEC changes in response to the storms. The skill score based on the metric scores is further proposed to evaluate the overall performance of ionospheric models against the reference model (International Reference Ionosphere 2016; IRI‐2016). The results indicate that the DA model GLObal Total Electron Content and JPL Global Ionospheric Map models show good performance in modeling the TEC and reasonably reflect the storm time TEC changes spatially and temporally. The empirical models IRI‐2016 and 2020 show relatively good performance compared with the physics‐based models regarding the model‐data comparison; however, it is difficult to characterize the TEC changes caused by storms. The physics‐based models can simulate the storm effect in spatial and temporal TEC variations better than the empirical model. The performance of ionospheric models in capturing the storm time TEC anomaly is presented and discussed.

show abstract

Section: Introductionmentioning

confidence: 99%

Validation of Ionospheric Modeled TEC in the Equatorial Ionosphere During the 2013 March and 2021 November Geomagnetic Storms

et al. 2023

View full text Add to dashboard Cite

show abstract

“…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). Unlike single‐station and regional forecasts that are usually trained with time series of TEC from different stations, global forecast models need to be trained with global TEC maps.…”

Section: Introductionmentioning

confidence: 99%

“…To the best of our knowledge, all global TEC forecast models mentioned above were trained with IGS GIMs or GIMs from a specific IAAC (Cesaroni et al., 2020; Chen et al., 2022; Lee et al., 2021; L. Liu et al., 2020, 2022; J. Tang et al., 2022; Xia, Zhang, et al., 2022; Yang et al., 2022) and achieved promising performance. Instead of aiming to outperform these models, this study aims to build a global TEC forecast model that uses the newly available VISTA TEC maps as input and can keep mesoscale structures in the output.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2023

View full text Add to dashboard Cite

This work developed a modified U‐Net model (a convolutional network architecture) to predict global Total Electron Content (TEC) maps. The input includes the current global TEC map, the current F10.7, the time history of the Interplanetary Magnetic Field Bz and SYM‐H in the previous 4 days, the Hour of Day, and the Day of Year. The output is the global TEC map several hours or several days ahead. The modified U‐Net was trained and validated on a brand new TEC database, the VISTA (Video Imputation with SoftImpute, Temporal smoothing and Auxiliary data) TEC database. The VISTA TEC maps can reveal important large‐scale TEC structures and preserve mesoscale structures simultaneously. Taking advantage of the new neural network and the new database, our model achieves an root of the mean squared error from 1.2 TECU to 2.4 TECU as the prediction horizon increases from 1 hr to 7 days. In addition, the model could reveal multiscale structures in the predicted TEC maps.

show abstract

“…For example, C. Wang et al (2018) proposed an adaptive autoregressive model to predict the SH coefficients used in TEC map fitting, while Iyer and Mahajan (2023) used both linear and polynomial autoregression coefficients of recent past data to forecast TEC over equatorial regions. L. Liu et al (2022) adopted a long short-term memory (LSTM) network to forecast the SH coefficient to predict the TEC maps further.…”

mentioning

confidence: 99%

Synthesis‐Style Auto‐Correlation‐Based Transformer: A Learner on Ionospheric TEC Series Forecasting

Yuan,

Xia,

Zhang

et al. 2023

Space Weather

View full text Add to dashboard Cite

Accurate 1‐day global total electron content (TEC) forecasting is essential for ionospheric monitoring and satellite communications. However, it faces challenges due to limited data and difficulty in modeling long‐term dependencies. This study develops a highly accurate model for 1‐day global TEC forecasting. We utilized generative TEC data augmentation based on the International Global Navigation Satellite Service (IGS) data set from 1998 to 2017 to enhance the model's prediction ability. Our model takes the TEC sequence of the previous 2 days as input and predicts the global TEC value for each hourly step of the next day. We compared the performance of our model with 1‐day predicted ionospheric products provided by both the Center for Orbit Determination in Europe (C1PG) and Beihang University (B1PG). We proposed a two‐step framework: (a) a time series generative model to produce realistic synthetic TEC data for training, and (b) an auto‐correlation‐based transformer model designed to capture long‐range dependencies in the TEC sequence. Experiments demonstrate that our model significantly improves 1‐day forecast accuracy over prior approaches. On the 2018 benchmark data set, the global root mean squared error (RMSE) of our model is reduced to 1.17 TEC units (TECU), while the RMSE of the C1PG model is 2.07 TECU. Reliability is higher in middle and high latitudes but lower in low latitudes (RMSE < 2.5 TECU), indicating room for improvement. This study highlights the potential of using data augmentation and auto‐correlation‐based transformer models trained on synthetic data to achieve high‐quality 1‐day global TEC forecasting.

show abstract

ML Prediction of Global Ionospheric TEC Maps

Cited by 19 publications

References 31 publications

Validation of Ionospheric Modeled TEC in the Equatorial Ionosphere During the 2013 March and 2021 November Geomagnetic Storms

Validation of Ionospheric Modeled TEC in the Equatorial Ionosphere During the 2013 March and 2021 November Geomagnetic Storms

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

Synthesis‐Style Auto‐Correlation‐Based Transformer: A Learner on Ionospheric TEC Series Forecasting

Contact Info

Product

Resources

About