Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress)
Abstract We advance the modeling capability of electron particle precipitation from the magnetosphere to the ionosphere through a new database and use of machine learning (ML) tools to gain utility from those data. We have compiled, curated, analyzed, and made available a new and more capable databa...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-06-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2020SW002684 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536433214455808 |
|---|---|
| author | Ryan M. McGranaghan Jack Ziegler Téo Bloch Spencer Hatch Enrico Camporeale Kristina Lynch Mathew Owens Jesper Gjerloev Binzheng Zhang Susan Skone |
| author_facet | Ryan M. McGranaghan Jack Ziegler Téo Bloch Spencer Hatch Enrico Camporeale Kristina Lynch Mathew Owens Jesper Gjerloev Binzheng Zhang Susan Skone |
| author_sort | Ryan M. McGranaghan |
| collection | DOAJ |
| description | Abstract We advance the modeling capability of electron particle precipitation from the magnetosphere to the ionosphere through a new database and use of machine learning (ML) tools to gain utility from those data. We have compiled, curated, analyzed, and made available a new and more capable database of particle precipitation data that includes 51 satellite years of Defense Meteorological Satellite Program (DMSP) observations temporally aligned with solar wind and geomagnetic activity data. The new total electron energy flux particle precipitation nowcast model, a neural network called PrecipNet, takes advantage of increased expressive power afforded by ML approaches to appropriately utilize diverse information from the solar wind and geomagnetic activity and, importantly, their time histories. With a more capable representation of the organizing parameters and the target electron energy flux observations, PrecipNet achieves a >50% reduction in errors from a current state‐of‐the‐art model oval variation, assessment, tracking, intensity, and online nowcasting (OVATION Prime), better captures the dynamic changes of the auroral flux, and provides evidence that it can capably reconstruct mesoscale phenomena. We create and apply a new framework for space weather model evaluation that culminates previous guidance from across the solar‐terrestrial research community. The research approach and results are representative of the “new frontier” of space weather research at the intersection of traditional and data science‐driven discovery and provides a foundation for future efforts. |
| format | Article |
| id | doaj-art-bc285c4bcc334511804ac1661c899de5 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2021-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-bc285c4bcc334511804ac1661c899de52025-01-14T16:30:36ZengWileySpace Weather1542-73902021-06-01196n/an/a10.1029/2020SW002684Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress)Ryan M. McGranaghan0Jack Ziegler1Téo Bloch2Spencer Hatch3Enrico Camporeale4Kristina Lynch5Mathew Owens6Jesper Gjerloev7Binzheng Zhang8Susan Skone9Atmosphere and Space Technology Research Associates (ASTRA) Louisville CO USAAtmosphere and Space Technology Research Associates (ASTRA) Louisville CO USAUniversity of Reading Reading EnglandBirkeland Center University of Bergen Bergen NorwayCIRES University of Colorado Boulder CO USADepartment of Physics and Astronomy Dartmouth College Hanover NH USAUniversity of Reading Reading EnglandBirkeland Center University of Bergen Bergen NorwayDepartment of Earth Sciences University of Hong Kong Kowloon Hong KongUniversity of Calgary Calgary AB CanadaAbstract We advance the modeling capability of electron particle precipitation from the magnetosphere to the ionosphere through a new database and use of machine learning (ML) tools to gain utility from those data. We have compiled, curated, analyzed, and made available a new and more capable database of particle precipitation data that includes 51 satellite years of Defense Meteorological Satellite Program (DMSP) observations temporally aligned with solar wind and geomagnetic activity data. The new total electron energy flux particle precipitation nowcast model, a neural network called PrecipNet, takes advantage of increased expressive power afforded by ML approaches to appropriately utilize diverse information from the solar wind and geomagnetic activity and, importantly, their time histories. With a more capable representation of the organizing parameters and the target electron energy flux observations, PrecipNet achieves a >50% reduction in errors from a current state‐of‐the‐art model oval variation, assessment, tracking, intensity, and online nowcasting (OVATION Prime), better captures the dynamic changes of the auroral flux, and provides evidence that it can capably reconstruct mesoscale phenomena. We create and apply a new framework for space weather model evaluation that culminates previous guidance from across the solar‐terrestrial research community. The research approach and results are representative of the “new frontier” of space weather research at the intersection of traditional and data science‐driven discovery and provides a foundation for future efforts.https://doi.org/10.1029/2020SW002684data scienceevaluationmachine learningmagnetosphere‐ionosphere couplingparticle precipitationspace weather |
| spellingShingle | Ryan M. McGranaghan Jack Ziegler Téo Bloch Spencer Hatch Enrico Camporeale Kristina Lynch Mathew Owens Jesper Gjerloev Binzheng Zhang Susan Skone Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress) Space Weather data science evaluation machine learning magnetosphere‐ionosphere coupling particle precipitation space weather |
| title | Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress) |
| title_full | Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress) |
| title_fullStr | Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress) |
| title_full_unstemmed | Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress) |
| title_short | Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress) |
| title_sort | toward a next generation particle precipitation model mesoscale prediction through machine learning a case study and framework for progress |
| topic | data science evaluation machine learning magnetosphere‐ionosphere coupling particle precipitation space weather |
| url | https://doi.org/10.1029/2020SW002684 |
| work_keys_str_mv | AT ryanmmcgranaghan towardanextgenerationparticleprecipitationmodelmesoscalepredictionthroughmachinelearningacasestudyandframeworkforprogress AT jackziegler towardanextgenerationparticleprecipitationmodelmesoscalepredictionthroughmachinelearningacasestudyandframeworkforprogress AT teobloch towardanextgenerationparticleprecipitationmodelmesoscalepredictionthroughmachinelearningacasestudyandframeworkforprogress AT spencerhatch towardanextgenerationparticleprecipitationmodelmesoscalepredictionthroughmachinelearningacasestudyandframeworkforprogress AT enricocamporeale towardanextgenerationparticleprecipitationmodelmesoscalepredictionthroughmachinelearningacasestudyandframeworkforprogress AT kristinalynch towardanextgenerationparticleprecipitationmodelmesoscalepredictionthroughmachinelearningacasestudyandframeworkforprogress AT mathewowens towardanextgenerationparticleprecipitationmodelmesoscalepredictionthroughmachinelearningacasestudyandframeworkforprogress AT jespergjerloev towardanextgenerationparticleprecipitationmodelmesoscalepredictionthroughmachinelearningacasestudyandframeworkforprogress AT binzhengzhang towardanextgenerationparticleprecipitationmodelmesoscalepredictionthroughmachinelearningacasestudyandframeworkforprogress AT susanskone towardanextgenerationparticleprecipitationmodelmesoscalepredictionthroughmachinelearningacasestudyandframeworkforprogress |