MEMPSEP‐I. Forecasting the Probability of Solar Energetic Particle Event Occurrence Using a Multivariate Ensemble of Convolutional Neural Networks
Abstract The Sun continuously affects the interplanetary environment through a host of interconnected and dynamic physical processes. Solar flares, Coronal Mass Ejections (CMEs), and Solar Energetic Particles (SEPs) are among the key drivers of space weather in the near‐Earth environment and beyond....
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-09-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2023SW003568 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536340477345792 |
|---|---|
| author | Subhamoy Chatterjee Maher A. Dayeh Andrés Muñoz‐Jaramillo Hazel M. Bain Kimberly Moreland Samuel Hart |
| author_facet | Subhamoy Chatterjee Maher A. Dayeh Andrés Muñoz‐Jaramillo Hazel M. Bain Kimberly Moreland Samuel Hart |
| author_sort | Subhamoy Chatterjee |
| collection | DOAJ |
| description | Abstract The Sun continuously affects the interplanetary environment through a host of interconnected and dynamic physical processes. Solar flares, Coronal Mass Ejections (CMEs), and Solar Energetic Particles (SEPs) are among the key drivers of space weather in the near‐Earth environment and beyond. While some CMEs and flares are associated with intense SEPs, some show little to no SEP association. To date, robust long‐term (hours‐days) forecasting of SEP occurrence and associated properties (e.g., onset, peak intensities) does not effectively exist and the search for such development continues. Through an Operations‐2‐Research support, we developed a self‐contained model that utilizes a comprehensive data set and provides a probabilistic forecast for SEP event occurrence and its properties. The model is named Multivariate Ensemble of Models for Probabilistic Forecast of Solar Energetic Particles (MEMPSEP). MEMPSEP workhorse is an ensemble of Convolutional Neural Networks that ingests a comprehensive data set (MEMPSEP‐III by Moreland et al. (2024, https://doi.org/10.1029/2023SW003765)) of full‐disc magnetogram‐sequences and in situ data from different sources to forecast the occurrence (MEMPSEP‐I—this work) and properties (MEMPSEP‐II by Dayeh et al. (2024, https://doi.org/10.1029/2023SW003697)) of a SEP event. This work focuses on estimating true SEP occurrence probabilities achieving a 2.5% improvement in reliability and a Brier score of 0.14. The outcome provides flexibility for the end‐users to determine their own acceptable level of risk, rather than imposing a detection threshold that optimizes an arbitrary binary classification metric. Furthermore, the model‐ensemble, trained to utilize the large class‐imbalance between events and non‐events, provides a clear measure of uncertainty in our forecast. |
| format | Article |
| id | doaj-art-8c6e6b44291b4185acfbb182436ae5fe |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-8c6e6b44291b4185acfbb182436ae5fe2025-01-14T16:35:30ZengWileySpace Weather1542-73902024-09-01229n/an/a10.1029/2023SW003568MEMPSEP‐I. Forecasting the Probability of Solar Energetic Particle Event Occurrence Using a Multivariate Ensemble of Convolutional Neural NetworksSubhamoy Chatterjee0Maher A. Dayeh1Andrés Muñoz‐Jaramillo2Hazel M. Bain3Kimberly Moreland4Samuel Hart5Southwest Research Institute Boulder CO USASouthwest Research Institute San Antonio TX USASouthwest Research Institute Boulder CO USACooperative Institute for Research in Environmental Sciences University of Boulder Boulder CO USASouthwest Research Institute San Antonio TX USASouthwest Research Institute San Antonio TX USAAbstract The Sun continuously affects the interplanetary environment through a host of interconnected and dynamic physical processes. Solar flares, Coronal Mass Ejections (CMEs), and Solar Energetic Particles (SEPs) are among the key drivers of space weather in the near‐Earth environment and beyond. While some CMEs and flares are associated with intense SEPs, some show little to no SEP association. To date, robust long‐term (hours‐days) forecasting of SEP occurrence and associated properties (e.g., onset, peak intensities) does not effectively exist and the search for such development continues. Through an Operations‐2‐Research support, we developed a self‐contained model that utilizes a comprehensive data set and provides a probabilistic forecast for SEP event occurrence and its properties. The model is named Multivariate Ensemble of Models for Probabilistic Forecast of Solar Energetic Particles (MEMPSEP). MEMPSEP workhorse is an ensemble of Convolutional Neural Networks that ingests a comprehensive data set (MEMPSEP‐III by Moreland et al. (2024, https://doi.org/10.1029/2023SW003765)) of full‐disc magnetogram‐sequences and in situ data from different sources to forecast the occurrence (MEMPSEP‐I—this work) and properties (MEMPSEP‐II by Dayeh et al. (2024, https://doi.org/10.1029/2023SW003697)) of a SEP event. This work focuses on estimating true SEP occurrence probabilities achieving a 2.5% improvement in reliability and a Brier score of 0.14. The outcome provides flexibility for the end‐users to determine their own acceptable level of risk, rather than imposing a detection threshold that optimizes an arbitrary binary classification metric. Furthermore, the model‐ensemble, trained to utilize the large class‐imbalance between events and non‐events, provides a clear measure of uncertainty in our forecast.https://doi.org/10.1029/2023SW003568 |
| spellingShingle | Subhamoy Chatterjee Maher A. Dayeh Andrés Muñoz‐Jaramillo Hazel M. Bain Kimberly Moreland Samuel Hart MEMPSEP‐I. Forecasting the Probability of Solar Energetic Particle Event Occurrence Using a Multivariate Ensemble of Convolutional Neural Networks Space Weather |
| title | MEMPSEP‐I. Forecasting the Probability of Solar Energetic Particle Event Occurrence Using a Multivariate Ensemble of Convolutional Neural Networks |
| title_full | MEMPSEP‐I. Forecasting the Probability of Solar Energetic Particle Event Occurrence Using a Multivariate Ensemble of Convolutional Neural Networks |
| title_fullStr | MEMPSEP‐I. Forecasting the Probability of Solar Energetic Particle Event Occurrence Using a Multivariate Ensemble of Convolutional Neural Networks |
| title_full_unstemmed | MEMPSEP‐I. Forecasting the Probability of Solar Energetic Particle Event Occurrence Using a Multivariate Ensemble of Convolutional Neural Networks |
| title_short | MEMPSEP‐I. Forecasting the Probability of Solar Energetic Particle Event Occurrence Using a Multivariate Ensemble of Convolutional Neural Networks |
| title_sort | mempsep i forecasting the probability of solar energetic particle event occurrence using a multivariate ensemble of convolutional neural networks |
| url | https://doi.org/10.1029/2023SW003568 |
| work_keys_str_mv | AT subhamoychatterjee mempsepiforecastingtheprobabilityofsolarenergeticparticleeventoccurrenceusingamultivariateensembleofconvolutionalneuralnetworks AT maheradayeh mempsepiforecastingtheprobabilityofsolarenergeticparticleeventoccurrenceusingamultivariateensembleofconvolutionalneuralnetworks AT andresmunozjaramillo mempsepiforecastingtheprobabilityofsolarenergeticparticleeventoccurrenceusingamultivariateensembleofconvolutionalneuralnetworks AT hazelmbain mempsepiforecastingtheprobabilityofsolarenergeticparticleeventoccurrenceusingamultivariateensembleofconvolutionalneuralnetworks AT kimberlymoreland mempsepiforecastingtheprobabilityofsolarenergeticparticleeventoccurrenceusingamultivariateensembleofconvolutionalneuralnetworks AT samuelhart mempsepiforecastingtheprobabilityofsolarenergeticparticleeventoccurrenceusingamultivariateensembleofconvolutionalneuralnetworks |