Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods
Abstract In this research, we present data‐driven forecasting of ionospheric total electron content (TEC) using the Long‐Short Term Memory (LSTM) deep recurrent neural network method. The random forest machine learning method was used to perform a regression analysis and estimate the variable import...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-06-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2020SW002639 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536389212012544 |
|---|---|
| author | Gebreab K. Zewdie Cesar Valladares Morris B. Cohen David J. Lary Dhanya Ramani Gizaw M. Tsidu |
| author_facet | Gebreab K. Zewdie Cesar Valladares Morris B. Cohen David J. Lary Dhanya Ramani Gizaw M. Tsidu |
| author_sort | Gebreab K. Zewdie |
| collection | DOAJ |
| description | Abstract In this research, we present data‐driven forecasting of ionospheric total electron content (TEC) using the Long‐Short Term Memory (LSTM) deep recurrent neural network method. The random forest machine learning method was used to perform a regression analysis and estimate the variable importance of the input parameters. The input data are obtained from satellite and ground based measurements characterizing the solar‐terrestrial environment. We estimate the relative importance of 34 different parameters, including the solar flux, solar wind density, and speed the three components of interplanetary magnetic field, Lyman‐alpha, the Kp, Dst, and Polar Cap (PC) indices. The TEC measurements are taken with 15‐s cadence from an equatorial GPS station located at Bogota, Columbia (4.7110° N, 74.0721° W). The 2008–2017 data set, including the top five parameters estimated using the random forest, is used for training the machine learning models, and the 2018 data set is used for independent testing of the LSTM forecasting. The LSTM method as applied to forecast the TEC up to 5 h ahead, with 30‐min cadence. The results indicate that very good forecasts with low root mean square (RMS) error (high correlation) can be made in the near future and the RMS errors increase as we forecast further into the future. The data sources are satellite and ground based measurements characterizing the solar‐terrestrial environment. |
| format | Article |
| id | doaj-art-23b6cc01d6fd4004ab1b87ec25d538fa |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2021-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-23b6cc01d6fd4004ab1b87ec25d538fa2025-01-14T16:30:36ZengWileySpace Weather1542-73902021-06-01196n/an/a10.1029/2020SW002639Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning MethodsGebreab K. Zewdie0Cesar Valladares1Morris B. Cohen2David J. Lary3Dhanya Ramani4Gizaw M. Tsidu5School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USAWilliam B. Hanson Center for Space Sciences University of Texas at Dallas Richardson TX USASchool of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USAWilliam B. Hanson Center for Space Sciences University of Texas at Dallas Richardson TX USAWilliam B. Hanson Center for Space Sciences University of Texas at Dallas Richardson TX USADepartment of Earth and Environmental Sciences Botswana International University of Science and Technology Palapye BotswanaAbstract In this research, we present data‐driven forecasting of ionospheric total electron content (TEC) using the Long‐Short Term Memory (LSTM) deep recurrent neural network method. The random forest machine learning method was used to perform a regression analysis and estimate the variable importance of the input parameters. The input data are obtained from satellite and ground based measurements characterizing the solar‐terrestrial environment. We estimate the relative importance of 34 different parameters, including the solar flux, solar wind density, and speed the three components of interplanetary magnetic field, Lyman‐alpha, the Kp, Dst, and Polar Cap (PC) indices. The TEC measurements are taken with 15‐s cadence from an equatorial GPS station located at Bogota, Columbia (4.7110° N, 74.0721° W). The 2008–2017 data set, including the top five parameters estimated using the random forest, is used for training the machine learning models, and the 2018 data set is used for independent testing of the LSTM forecasting. The LSTM method as applied to forecast the TEC up to 5 h ahead, with 30‐min cadence. The results indicate that very good forecasts with low root mean square (RMS) error (high correlation) can be made in the near future and the RMS errors increase as we forecast further into the future. The data sources are satellite and ground based measurements characterizing the solar‐terrestrial environment.https://doi.org/10.1029/2020SW002639LSTMTEC forecastingrandom forestspace weatherionosphere |
| spellingShingle | Gebreab K. Zewdie Cesar Valladares Morris B. Cohen David J. Lary Dhanya Ramani Gizaw M. Tsidu Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods Space Weather LSTM TEC forecasting random forest space weather ionosphere |
| title | Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods |
| title_full | Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods |
| title_fullStr | Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods |
| title_full_unstemmed | Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods |
| title_short | Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods |
| title_sort | data driven forecasting of low latitude ionospheric total electron content using the random forest and lstm machine learning methods |
| topic | LSTM TEC forecasting random forest space weather ionosphere |
| url | https://doi.org/10.1029/2020SW002639 |
| work_keys_str_mv | AT gebreabkzewdie datadrivenforecastingoflowlatitudeionospherictotalelectroncontentusingtherandomforestandlstmmachinelearningmethods AT cesarvalladares datadrivenforecastingoflowlatitudeionospherictotalelectroncontentusingtherandomforestandlstmmachinelearningmethods AT morrisbcohen datadrivenforecastingoflowlatitudeionospherictotalelectroncontentusingtherandomforestandlstmmachinelearningmethods AT davidjlary datadrivenforecastingoflowlatitudeionospherictotalelectroncontentusingtherandomforestandlstmmachinelearningmethods AT dhanyaramani datadrivenforecastingoflowlatitudeionospherictotalelectroncontentusingtherandomforestandlstmmachinelearningmethods AT gizawmtsidu datadrivenforecastingoflowlatitudeionospherictotalelectroncontentusingtherandomforestandlstmmachinelearningmethods |