A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population
Abstract The high energy particles originating from the Sun, known as solar energetic particles (SEPs), contribute significantly to the space radiation environment, posing serious threats to astronauts and scientific instruments on board spacecraft. The mechanism that accelerates the SEPs to the obs...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-12-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023SW003593 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536424109670400 |
|---|---|
| author | Atilim Guneş Baydin Bala Poduval Nathan A. Schwadron |
| author_facet | Atilim Guneş Baydin Bala Poduval Nathan A. Schwadron |
| author_sort | Atilim Guneş Baydin |
| collection | DOAJ |
| description | Abstract The high energy particles originating from the Sun, known as solar energetic particles (SEPs), contribute significantly to the space radiation environment, posing serious threats to astronauts and scientific instruments on board spacecraft. The mechanism that accelerates the SEPs to the observed energy ranges, their transport in the inner heliosphere, and the influence of suprathermal seed particle spectrum are open questions in heliophysics. Accurate predictions of the occurrences of SEP events well in advance are necessary to mitigate their adverse effects but prediction based on first principle models still remains a challenge. In this scenario, adopting a machine learning approach to SEP modeling and prediction is desirable. However, the lack of a balanced database of SEP events restrains this approach. We addressed this limitation by generating large data sets of synthetic SEP events sampled from the physics‐based model, Energetic Particle Radiation Environment Module (EPREM). Using this data, we developed neural networks‐based surrogate models to study the seed population parameter space. Our models, EPREM‐S, run thousands to millions of times faster (depending on computer hardware), making simulation‐based inference workflows practicable in SEP studies while providing predictive uncertainty estimates using a deep ensemble approach. |
| format | Article |
| id | doaj-art-9c40207780e64ad8a36474b1f96bc645 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2023-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-9c40207780e64ad8a36474b1f96bc6452025-01-14T16:30:45ZengWileySpace Weather1542-73902023-12-012112n/an/a10.1029/2023SW003593A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed PopulationAtilim Guneş Baydin0Bala Poduval1Nathan A. Schwadron2Department of Computer Science University of Oxford Oxford UKSpace Science Center University of New Hampshire Durham NH USASpace Science Center University of New Hampshire Durham NH USAAbstract The high energy particles originating from the Sun, known as solar energetic particles (SEPs), contribute significantly to the space radiation environment, posing serious threats to astronauts and scientific instruments on board spacecraft. The mechanism that accelerates the SEPs to the observed energy ranges, their transport in the inner heliosphere, and the influence of suprathermal seed particle spectrum are open questions in heliophysics. Accurate predictions of the occurrences of SEP events well in advance are necessary to mitigate their adverse effects but prediction based on first principle models still remains a challenge. In this scenario, adopting a machine learning approach to SEP modeling and prediction is desirable. However, the lack of a balanced database of SEP events restrains this approach. We addressed this limitation by generating large data sets of synthetic SEP events sampled from the physics‐based model, Energetic Particle Radiation Environment Module (EPREM). Using this data, we developed neural networks‐based surrogate models to study the seed population parameter space. Our models, EPREM‐S, run thousands to millions of times faster (depending on computer hardware), making simulation‐based inference workflows practicable in SEP studies while providing predictive uncertainty estimates using a deep ensemble approach.https://doi.org/10.1029/2023SW003593surrogate modelneural networksolar energetic particleuncertainty quantificationseed populationEPREM |
| spellingShingle | Atilim Guneş Baydin Bala Poduval Nathan A. Schwadron A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population Space Weather surrogate model neural network solar energetic particle uncertainty quantification seed population EPREM |
| title | A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population |
| title_full | A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population |
| title_fullStr | A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population |
| title_full_unstemmed | A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population |
| title_short | A Surrogate Model for Studying Solar Energetic Particle Transport and the Seed Population |
| title_sort | surrogate model for studying solar energetic particle transport and the seed population |
| topic | surrogate model neural network solar energetic particle uncertainty quantification seed population EPREM |
| url | https://doi.org/10.1029/2023SW003593 |
| work_keys_str_mv | AT atilimgunesbaydin asurrogatemodelforstudyingsolarenergeticparticletransportandtheseedpopulation AT balapoduval asurrogatemodelforstudyingsolarenergeticparticletransportandtheseedpopulation AT nathanaschwadron asurrogatemodelforstudyingsolarenergeticparticletransportandtheseedpopulation AT atilimgunesbaydin surrogatemodelforstudyingsolarenergeticparticletransportandtheseedpopulation AT balapoduval surrogatemodelforstudyingsolarenergeticparticletransportandtheseedpopulation AT nathanaschwadron surrogatemodelforstudyingsolarenergeticparticletransportandtheseedpopulation |