Probabilistic Forecasts of Storm Sudden Commencements From Interplanetary Shocks Using Machine Learning
Abstract In this study we investigate the ability of several different machine learning models to provide probabilistic predictions as to whether interplanetary shocks observed upstream of the Earth at L1 will lead to immediate (Sudden Commencements, SCs) or longer lasting magnetospheric activity (S...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-11-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2020SW002603 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536382867079168 |
|---|---|
| author | A. W. Smith I. J. Rae C. Forsyth D. M. Oliveira M. P. Freeman D. R. Jackson |
| author_facet | A. W. Smith I. J. Rae C. Forsyth D. M. Oliveira M. P. Freeman D. R. Jackson |
| author_sort | A. W. Smith |
| collection | DOAJ |
| description | Abstract In this study we investigate the ability of several different machine learning models to provide probabilistic predictions as to whether interplanetary shocks observed upstream of the Earth at L1 will lead to immediate (Sudden Commencements, SCs) or longer lasting magnetospheric activity (Storm Sudden Commencements, SSCs). Four models are tested including linear (Logistic Regression), nonlinear (Naive Bayes and Gaussian Process), and ensemble (Random Forest) models and are shown to provide skillful and reliable forecasts of SCs with Brier Skill Scores (BSSs) of ∼0.3 and ROC scores >0.8. The most powerful predictive parameter is found to be the range in the interplanetary magnetic field. The models also produce skillful forecasts of SSCs, though with less reliability than was found for SCs. The BSSs and ROC scores returned are ∼0.21 and 0.82, respectively. The most important parameter for these predictions was found to be the minimum observed BZ. The simple parameterization of the shock was tested by including additional features related to magnetospheric indices and their changes during shock impact, resulting in moderate increases in reliability. Several parameters, such as velocity and density, may be able to be more accurately predicted at a longer lead time, for example, from heliospheric imagery. When the input was limited to the velocity and density the models were found to perform well at forecasting SSCs, though with lower reliability than previously (BSSs ∼ 0.16, ROC Scores ∼ 0.8), Finally, the models were tested with hypothetical extreme data beyond current observations, showing dramatically different extrapolations. |
| format | Article |
| id | doaj-art-0e9ea60bedea487686fab39cc13a2c46 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2020-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-0e9ea60bedea487686fab39cc13a2c462025-01-14T16:30:47ZengWileySpace Weather1542-73902020-11-011811n/an/a10.1029/2020SW002603Probabilistic Forecasts of Storm Sudden Commencements From Interplanetary Shocks Using Machine LearningA. W. Smith0I. J. Rae1C. Forsyth2D. M. Oliveira3M. P. Freeman4D. R. Jackson5Mullard Space Science Laboratory UCL Dorking UKMullard Space Science Laboratory UCL Dorking UKMullard Space Science Laboratory UCL Dorking UKGoddard Planetary Heliophysics Institute University of Maryland, Baltimore County Baltimore MD USABritish Antarctic Survey Cambridge UKMet Office Exeter UKAbstract In this study we investigate the ability of several different machine learning models to provide probabilistic predictions as to whether interplanetary shocks observed upstream of the Earth at L1 will lead to immediate (Sudden Commencements, SCs) or longer lasting magnetospheric activity (Storm Sudden Commencements, SSCs). Four models are tested including linear (Logistic Regression), nonlinear (Naive Bayes and Gaussian Process), and ensemble (Random Forest) models and are shown to provide skillful and reliable forecasts of SCs with Brier Skill Scores (BSSs) of ∼0.3 and ROC scores >0.8. The most powerful predictive parameter is found to be the range in the interplanetary magnetic field. The models also produce skillful forecasts of SSCs, though with less reliability than was found for SCs. The BSSs and ROC scores returned are ∼0.21 and 0.82, respectively. The most important parameter for these predictions was found to be the minimum observed BZ. The simple parameterization of the shock was tested by including additional features related to magnetospheric indices and their changes during shock impact, resulting in moderate increases in reliability. Several parameters, such as velocity and density, may be able to be more accurately predicted at a longer lead time, for example, from heliospheric imagery. When the input was limited to the velocity and density the models were found to perform well at forecasting SSCs, though with lower reliability than previously (BSSs ∼ 0.16, ROC Scores ∼ 0.8), Finally, the models were tested with hypothetical extreme data beyond current observations, showing dramatically different extrapolations.https://doi.org/10.1029/2020SW002603forecastinterplanetary shockmachine leaningspace weatherSudden Commencement |
| spellingShingle | A. W. Smith I. J. Rae C. Forsyth D. M. Oliveira M. P. Freeman D. R. Jackson Probabilistic Forecasts of Storm Sudden Commencements From Interplanetary Shocks Using Machine Learning Space Weather forecast interplanetary shock machine leaning space weather Sudden Commencement |
| title | Probabilistic Forecasts of Storm Sudden Commencements From Interplanetary Shocks Using Machine Learning |
| title_full | Probabilistic Forecasts of Storm Sudden Commencements From Interplanetary Shocks Using Machine Learning |
| title_fullStr | Probabilistic Forecasts of Storm Sudden Commencements From Interplanetary Shocks Using Machine Learning |
| title_full_unstemmed | Probabilistic Forecasts of Storm Sudden Commencements From Interplanetary Shocks Using Machine Learning |
| title_short | Probabilistic Forecasts of Storm Sudden Commencements From Interplanetary Shocks Using Machine Learning |
| title_sort | probabilistic forecasts of storm sudden commencements from interplanetary shocks using machine learning |
| topic | forecast interplanetary shock machine leaning space weather Sudden Commencement |
| url | https://doi.org/10.1029/2020SW002603 |
| work_keys_str_mv | AT awsmith probabilisticforecastsofstormsuddencommencementsfrominterplanetaryshocksusingmachinelearning AT ijrae probabilisticforecastsofstormsuddencommencementsfrominterplanetaryshocksusingmachinelearning AT cforsyth probabilisticforecastsofstormsuddencommencementsfrominterplanetaryshocksusingmachinelearning AT dmoliveira probabilisticforecastsofstormsuddencommencementsfrominterplanetaryshocksusingmachinelearning AT mpfreeman probabilisticforecastsofstormsuddencommencementsfrominterplanetaryshocksusingmachinelearning AT drjackson probabilisticforecastsofstormsuddencommencementsfrominterplanetaryshocksusingmachinelearning |