A Prediction Model of Relativistic Electrons at Geostationary Orbit Using the EMD‐LSTM Network and Geomagnetic Indices
Abstract In this study, the Empirical Mode Decomposition algorithm (EMD) and the Long Short Term Memory neural network (LSTM) are combined into an EMD‐LSTM model, to predict the variation of the >2 MeV electron fluxes 1 day ahead. Input parameters include the Pc5 power, AP, AE, Kp, >0.6 MeV, a...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-10-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2022SW003126 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536420653563904 |
|---|---|
| author | H. Zhang H. R. Xu G. S. Peng Y. D. Qian X. X. Zhang G. L. Yang C. Shen Z. Li J. W. Yang Z. Q. Wang F. He C. L. Gu M. B. Zhu |
| author_facet | H. Zhang H. R. Xu G. S. Peng Y. D. Qian X. X. Zhang G. L. Yang C. Shen Z. Li J. W. Yang Z. Q. Wang F. He C. L. Gu M. B. Zhu |
| author_sort | H. Zhang |
| collection | DOAJ |
| description | Abstract In this study, the Empirical Mode Decomposition algorithm (EMD) and the Long Short Term Memory neural network (LSTM) are combined into an EMD‐LSTM model, to predict the variation of the >2 MeV electron fluxes 1 day ahead. Input parameters include the Pc5 power, AP, AE, Kp, >0.6 MeV, and historical electron flux values, are used for predictions. All the time resolution of parameters are daily integral values. As compared the prediction results of the EMD‐LSTM model with other classical prediction models, the results show that the 1 day ahead prediction efficiency of the >2 MeV electron fluxes possesses a prediction efficiency of 0.80, and the highest prediction efficiency can reach 0.93. These results are superior to the prediction accuracy of more previous models. Using two high‐energy electron flux storm events for validation, the results indicate that the performance of the EMD‐LSTM model in the period of the high‐energy electron flux storm is also relatively good, especially for the prediction of high‐energy electron fluxes at extreme points, and the predictions are closer to actual observations. |
| format | Article |
| id | doaj-art-967d1b614e4e4791b68fc2d07056fde1 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2022-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-967d1b614e4e4791b68fc2d07056fde12025-01-14T16:30:48ZengWileySpace Weather1542-73902022-10-012010n/an/a10.1029/2022SW003126A Prediction Model of Relativistic Electrons at Geostationary Orbit Using the EMD‐LSTM Network and Geomagnetic IndicesH. Zhang0H. R. Xu1G. S. Peng2Y. D. Qian3X. X. Zhang4G. L. Yang5C. Shen6Z. Li7J. W. Yang8Z. Q. Wang9F. He10C. L. Gu11M. B. Zhu12Institute of Space Weather Nanjing University of Information Science & Technology Nanjing ChinaInstitute of Space Weather Nanjing University of Information Science & Technology Nanjing ChinaInstitute of Space Weather Nanjing University of Information Science & Technology Nanjing ChinaInstitute of Space Weather Nanjing University of Information Science & Technology Nanjing ChinaKey Laboratory of Space Weather National Center for Space Weather China Meteorological Administration Beijing ChinaKey Laboratory of Space Weather National Center for Space Weather China Meteorological Administration Beijing ChinaHarbin Institute of Technology Shen Zhen ChinaInstitute of Space Weather Nanjing University of Information Science & Technology Nanjing ChinaInstitute of Space Weather Nanjing University of Information Science & Technology Nanjing ChinaCollege of Astronautics Nanjing University of Aeronautics and Astronautics Nanjing ChinaNMR Key Laboratory for Polar Science Polar Research Institute of China Shang Hai ChinaBeijing Institute of Applied Meteorology Beijing ChinaBeijing Institute of Applied Meteorology Beijing ChinaAbstract In this study, the Empirical Mode Decomposition algorithm (EMD) and the Long Short Term Memory neural network (LSTM) are combined into an EMD‐LSTM model, to predict the variation of the >2 MeV electron fluxes 1 day ahead. Input parameters include the Pc5 power, AP, AE, Kp, >0.6 MeV, and historical electron flux values, are used for predictions. All the time resolution of parameters are daily integral values. As compared the prediction results of the EMD‐LSTM model with other classical prediction models, the results show that the 1 day ahead prediction efficiency of the >2 MeV electron fluxes possesses a prediction efficiency of 0.80, and the highest prediction efficiency can reach 0.93. These results are superior to the prediction accuracy of more previous models. Using two high‐energy electron flux storm events for validation, the results indicate that the performance of the EMD‐LSTM model in the period of the high‐energy electron flux storm is also relatively good, especially for the prediction of high‐energy electron fluxes at extreme points, and the predictions are closer to actual observations.https://doi.org/10.1029/2022SW003126 |
| spellingShingle | H. Zhang H. R. Xu G. S. Peng Y. D. Qian X. X. Zhang G. L. Yang C. Shen Z. Li J. W. Yang Z. Q. Wang F. He C. L. Gu M. B. Zhu A Prediction Model of Relativistic Electrons at Geostationary Orbit Using the EMD‐LSTM Network and Geomagnetic Indices Space Weather |
| title | A Prediction Model of Relativistic Electrons at Geostationary Orbit Using the EMD‐LSTM Network and Geomagnetic Indices |
| title_full | A Prediction Model of Relativistic Electrons at Geostationary Orbit Using the EMD‐LSTM Network and Geomagnetic Indices |
| title_fullStr | A Prediction Model of Relativistic Electrons at Geostationary Orbit Using the EMD‐LSTM Network and Geomagnetic Indices |
| title_full_unstemmed | A Prediction Model of Relativistic Electrons at Geostationary Orbit Using the EMD‐LSTM Network and Geomagnetic Indices |
| title_short | A Prediction Model of Relativistic Electrons at Geostationary Orbit Using the EMD‐LSTM Network and Geomagnetic Indices |
| title_sort | prediction model of relativistic electrons at geostationary orbit using the emd lstm network and geomagnetic indices |
| url | https://doi.org/10.1029/2022SW003126 |
| work_keys_str_mv | AT hzhang apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT hrxu apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT gspeng apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT ydqian apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT xxzhang apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT glyang apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT cshen apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT zli apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT jwyang apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT zqwang apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT fhe apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT clgu apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT mbzhu apredictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT hzhang predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT hrxu predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT gspeng predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT ydqian predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT xxzhang predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT glyang predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT cshen predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT zli predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT jwyang predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT zqwang predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT fhe predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT clgu predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices AT mbzhu predictionmodelofrelativisticelectronsatgeostationaryorbitusingtheemdlstmnetworkandgeomagneticindices |