Modeling Ionospheric TEC Using Gradient Boosting Based and Stacking Machine Learning Techniques
Abstract Accurately predicting and modeling the ionospheric total electron content (TEC) can greatly improve the accuracy of satellite navigation and positioning and help to correct ionospheric delay. This study assesses the effectiveness of four different machine learning (ML) models in predicting...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-03-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023SW003821 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536404607205376 |
|---|---|
| author | Ayanew Nigusie Ambelu Tebabal Roman Galas |
| author_facet | Ayanew Nigusie Ambelu Tebabal Roman Galas |
| author_sort | Ayanew Nigusie |
| collection | DOAJ |
| description | Abstract Accurately predicting and modeling the ionospheric total electron content (TEC) can greatly improve the accuracy of satellite navigation and positioning and help to correct ionospheric delay. This study assesses the effectiveness of four different machine learning (ML) models in predicting hourly vertical TEC (VTEC) data for a single‐station study over Ethiopia. The models employed include gradient boosting machine (GBM), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM) algorithms, and a stacked combination of these algorithms with a linear regression algorithm. The models relied on input variables that represent solar activity, geomagnetic activity, season, time of the day, interplanetary magnetic field, and solar wind. The models were trained using the VTEC data from January 2011 to December 2018, excluding the testing data. The testing data comprised the data for the year 2015 and the initial 6 months of 2017. The RandomizedSearchCV algorithm was used to determine the optimal hyperparameters of the models. The predicted VTEC values of the four ML models were strongly correlated with the GPS VTEC, with a correlation coefficient of ∼0.96, which is significantly higher than the corresponding value of the International Reference Ionosphere (IRI 2020) model, which is 0.87. Comparing the GPS VTEC values with the predicted VTEC values based on diurnal and seasonal characteristics showed that the predictions of the developed models were generally in good agreement and outperformed the IRI 2020 model. Overall, the ML models used in this study demonstrated promising potential for accurate single‐station VTEC prediction over Ethiopia. |
| format | Article |
| id | doaj-art-5ae75f8213c447119dabbec00ecb4867 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2024-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-5ae75f8213c447119dabbec00ecb48672025-01-14T16:30:30ZengWileySpace Weather1542-73902024-03-01223n/an/a10.1029/2023SW003821Modeling Ionospheric TEC Using Gradient Boosting Based and Stacking Machine Learning TechniquesAyanew Nigusie0Ambelu Tebabal1Roman Galas2Department of Physics Washera Geospace and Radar Science Research Laboratory Bahir Dar University Bahir Dar EthiopiaDepartment of Physics Washera Geospace and Radar Science Research Laboratory Bahir Dar University Bahir Dar EthiopiaInstitute of Geodesy and Geoinformation Science Chair of Precision Navigation and ‐Positioning, Technical University of Berlin Berlin GermanyAbstract Accurately predicting and modeling the ionospheric total electron content (TEC) can greatly improve the accuracy of satellite navigation and positioning and help to correct ionospheric delay. This study assesses the effectiveness of four different machine learning (ML) models in predicting hourly vertical TEC (VTEC) data for a single‐station study over Ethiopia. The models employed include gradient boosting machine (GBM), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM) algorithms, and a stacked combination of these algorithms with a linear regression algorithm. The models relied on input variables that represent solar activity, geomagnetic activity, season, time of the day, interplanetary magnetic field, and solar wind. The models were trained using the VTEC data from January 2011 to December 2018, excluding the testing data. The testing data comprised the data for the year 2015 and the initial 6 months of 2017. The RandomizedSearchCV algorithm was used to determine the optimal hyperparameters of the models. The predicted VTEC values of the four ML models were strongly correlated with the GPS VTEC, with a correlation coefficient of ∼0.96, which is significantly higher than the corresponding value of the International Reference Ionosphere (IRI 2020) model, which is 0.87. Comparing the GPS VTEC values with the predicted VTEC values based on diurnal and seasonal characteristics showed that the predictions of the developed models were generally in good agreement and outperformed the IRI 2020 model. Overall, the ML models used in this study demonstrated promising potential for accurate single‐station VTEC prediction over Ethiopia.https://doi.org/10.1029/2023SW003821total electron contentXGBoostLightGBMgradient boosting machinestackingmachine learning |
| spellingShingle | Ayanew Nigusie Ambelu Tebabal Roman Galas Modeling Ionospheric TEC Using Gradient Boosting Based and Stacking Machine Learning Techniques Space Weather total electron content XGBoost LightGBM gradient boosting machine stacking machine learning |
| title | Modeling Ionospheric TEC Using Gradient Boosting Based and Stacking Machine Learning Techniques |
| title_full | Modeling Ionospheric TEC Using Gradient Boosting Based and Stacking Machine Learning Techniques |
| title_fullStr | Modeling Ionospheric TEC Using Gradient Boosting Based and Stacking Machine Learning Techniques |
| title_full_unstemmed | Modeling Ionospheric TEC Using Gradient Boosting Based and Stacking Machine Learning Techniques |
| title_short | Modeling Ionospheric TEC Using Gradient Boosting Based and Stacking Machine Learning Techniques |
| title_sort | modeling ionospheric tec using gradient boosting based and stacking machine learning techniques |
| topic | total electron content XGBoost LightGBM gradient boosting machine stacking machine learning |
| url | https://doi.org/10.1029/2023SW003821 |
| work_keys_str_mv | AT ayanewnigusie modelingionospherictecusinggradientboostingbasedandstackingmachinelearningtechniques AT ambelutebabal modelingionospherictecusinggradientboostingbasedandstackingmachinelearningtechniques AT romangalas modelingionospherictecusinggradientboostingbasedandstackingmachinelearningtechniques |