Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods

Zewdie, Gebreab K.; Valladares, C. E.; Cohen, M. B.; Lary, David J.; Ramani, Dhanya; Tsidu, Gizaw Mengistu

doi:10.1029/2020sw002639

Cited by 32 publications

(26 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results of the model established for station HRBN showed that the RMSE of the ED-LSTME model was 1.455 TECU, which is obviously larger than the RMSEs of the bi-LSTM model for the 1 hr (0.743 TECU) and 2 hr (0.998 TECU) ahead predictions tested in this study. Zewdie et al (2021) applied an LSTM method to predict the TEC at an equatorial GPS station up to 5 hr ahead, with a 30-min interval, and results indicated that the correlation coefficient decreased while the RMSE increased as the time of the prediction is further into the future. Moreover Finally, the new model captures the variations of the ionosphere TEC under geomagnetic storm conditions.…”

Section: Discussionmentioning

confidence: 99%

“…Zewdie et al. (2021) applied an LSTM method to predict the TEC at an equatorial GPS station up to 5 hr ahead, with a 30‐min interval, and results indicated that the correlation coefficient decreased while the RMSE increased as the time of the prediction is further into the future. Moreover, Chen et al.…”

Section: Discussionmentioning

confidence: 99%

“…Deep learning methods have been widely used in the prediction of the ionospheric TEC for a single station (Huang et al., 2015; Kaselimi et al., 2020; Ruwali et al., 2021; Srivani et al., 2019; Xiong et al., 2021; Zewdie et al., 2021), for a region (Li et al., 2020; Okoh et al., 2016, 2019, 2020; Razin et al., 2015; Sabzehee et al., 2018; Song et al., 2018; Tebabal et al., 2019; Uwamahoro et al., 2018), and for the globe (Cesaroni et al., 2020; Chen et al., 2019; Liu et al., 2020; Zhukov et al., 2020). TEC prediction models for a single station based on the artificial neural network (ANN) method (Huang et al., 2015; Huang & Yuan, 2014), the long short‐term memory (LSTM) method (Kaselimi et al., 2020; Srivani et al., 2019; Xiong et al., 2021; Zewdie et al., 2021), and the hybrid deep learning method (Ruwali et al., 2021), all have recently shown promising results. Both the LSTM and hybrid deep learning methods have shown better performance than the ANN method.…”

Section: Introductionmentioning

confidence: 99%

“…For these two aspects, deep learning methods are promising as they are well known for progressively extracting higher‐level features from the raw input variables, and one of the benefits is that there is no need to identify or specify the functional relationship (e.g., linear or nonlinear) of the model. This is why deep learning methods are often used to model the ionospheric TEC (Li, Zhao, et al., 2021; Ruwali et al., 2021; Xiong et al., 2021; Zewdie et al., 2021; Zhukov et al., 2020).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Investigation of Ionospheric TEC Prediction Maps Over China Using Bidirectional Long Short‐Term Memory Method

Shi

Zhang

et al. 2022

Space Weather

View full text Add to dashboard Cite

The ionospheric total electron content (TEC) is an important ionospheric parameter, and it is widely utilized in research such as space weather prediction and precise positioning. However, it is still challenging to develop an ionospheric TEC prediction model with high accuracy. In this study, a new ionospheric TEC model over China was developed using the bidirectional long short‐term memory (bi‐LSTM) method and observations from 257 ground‐based global navigation satellite system (GNSS) stations in the Crustal Movement Observation Network of China from January 2018 to December 2021. The root mean square errors of the bi‐LSTM‐based model’s 1 and 2 hr ahead predictions on the test data set (from June 2021 to December 2021) are 1.12 and 1.68 TECU, respectively, which are 75/50/32% and 72/48/22% smaller than those of the IRI‐2016, artificial neural network and LSTM‐based models, correspondingly. The bi‐LSTM‐based model shows the best performance, which is most likely due to the fact that the sequence information in both forward and backward directions is taken into consideration in the new model. In addition, the diurnal variation, seasonal variation of the ionospheric TEC, and variations under geomagnetic storm conditions are successfully captured by the bi‐LSTM‐based model. Moreover, the TEC maps resulting from the bi‐LSTM model agree well with those obtained from the final ionospheric product from the Chinese Academy of Sciences. Hence, the new model can be a good choice for the investigation of the spatiotemporal variation trend in the ionosphere and GNSS navigation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Investigation of Ionospheric TEC Prediction Maps Over China Using Bidirectional Long Short‐Term Memory Method

Shi

Zhang

et al. 2022

Space Weather

View full text Add to dashboard Cite

show abstract

“…Thus, such processing methods theoretically introduce more model errors and some original ionospheric information is lost in the forecast stage. Secondly, because of the continuous forecast, the error accumulation phenomenon occurs as the forecast hour increases within a day (Ruwali et al, 2021;Zewdie et al, 2021). Many studies have been done on the variation characteristics of the ionosphere, showing that the ionosphere mainly presents periodic regular variation patterns such as 11-year cycle variation, seasonal variation and diurnal variation.…”

Section: Introductionmentioning

confidence: 99%

LSTM-based short-term ionospheric TEC forecast model and position accuracy analysis

Xie

Dai

Zhu

et al. 2022

Preprint

View full text Add to dashboard Cite

Ionospheric delay is one of the major error sources in global navigation satellite system (GNSS) single point positioning (SPP). Some empirical models have been proposed to correct ionospheric delay, which, however, are limited by the low accuracy. The single-point time-series-based ionospheric total electron content (TEC) forecast method theoretically introduces model error and the accumulation of forecast error increases during a day. Therefore, based on the regular variation characteristics of the ionosphere, to improve the forecast accuracy of the ionosphere, we propose a long short-term memory (LSTM) short-term forecast model using discrete GNSS data and ionospheric space environment data in the same period of multiple days. The LSTM ionospheric forecast model is constructed based on the 2014 single-site GNSS data from different regions (low, mid, and high latitude regions) of the Crustal Movement Observation Network of China (CMONOC). The results are compared with the Klobuchar model, CMONOC regional ionosphere maps (RIM) data, and GNSS derived TEC measurements. The performance of each model in the SPP is also compared and analyzed to further examine the feasibility of the LSTM ionospheric forecast model. The comprehensive statistical analysis shows that: i) LSTM forecast model is consistent with GNSS-TEC observations at high, mid, and low latitudes, and the forecast error is less than 3 TECu, which is much better than that of the Klobuchar model and RIM model, and is robust to anomalous values. The mean absolute error (MAE) and root mean square error (RMSE) of the LSTM forecast model decrease with increasing latitude. ii) When being used in SPP, the LSTM forecast model brings significant improvement to position accuracy, which is overall better than the RIM and Klobuchar models. The RMSE of 3D position error is 2–4 m for the LSTM forecast model, 2–5 m for the RIM model, and 4–5 m for the Klobuchar model. iii) In terms of geographic location, for 3D position accuracy, it is highest at mid-latitudes followed by high latitudes and worst at low latitudes. For the percentage of 3D position corrections relative to the reference, it is highest at high latitudes followed by mid-latitudes, and lowest at low latitudes. The percentage of LSTM forecast model is 85%-90% at low latitudes, which is better than Klobuchar's 40%-80% and RIM's 75%-85%. Such percentage is over 90% at mid-latitudes, which is comparable to the RIM and about 50% better than the Klobuchar model. It is noteworthy that the LSTM performs even better than the reference data at high latitudes.

show abstract

A storm-time ionospheric TEC model with multichannel features by the spatiotemporal ConvLSTM network

Gao

Yao

2023

J Geod

View full text Add to dashboard Cite

Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods

Abstract: The random forest and LSTM methods are employed, the data sources are space 13 measurements characterizing the solar-terrestrial environment 14• Variable importance ranking showed that F10.7, Lyman alpha are top predictors 15 agreeing well with the physics of ionospheric formation

Cited by 32 publications

References 51 publications

An Investigation of Ionospheric TEC Prediction Maps Over China Using Bidirectional Long Short‐Term Memory Method

An Investigation of Ionospheric TEC Prediction Maps Over China Using Bidirectional Long Short‐Term Memory Method

LSTM-based short-term ionospheric TEC forecast model and position accuracy analysis

A storm-time ionospheric TEC model with multichannel features by the spatiotemporal ConvLSTM network

Contact Info

Product

Resources

About