Medium Energy Electron Flux in Earth's Outer Radiation Belt (MERLIN): A Machine Learning Model
Abstract The radiation belts of the Earth, filled with energetic electrons, comprise complex and dynamic systems that pose a significant threat to satellite operation. While various models of electron flux both for low and relativistic energies have been developed, the behavior of medium energy (120...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-11-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2020SW002532 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536440701288448 |
|---|---|
| author | A. G. Smirnov M. Berrendorf Y. Y. Shprits E. A. Kronberg H. J. Allison N. A. Aseev I. S. Zhelavskaya S. K. Morley G. D. Reeves M. R. Carver F. Effenberger |
| author_facet | A. G. Smirnov M. Berrendorf Y. Y. Shprits E. A. Kronberg H. J. Allison N. A. Aseev I. S. Zhelavskaya S. K. Morley G. D. Reeves M. R. Carver F. Effenberger |
| author_sort | A. G. Smirnov |
| collection | DOAJ |
| description | Abstract The radiation belts of the Earth, filled with energetic electrons, comprise complex and dynamic systems that pose a significant threat to satellite operation. While various models of electron flux both for low and relativistic energies have been developed, the behavior of medium energy (120–600 keV) electrons, especially in the MEO region, remains poorly quantified. At these energies, electrons are driven by both convective and diffusive transport, and their prediction usually requires sophisticated 4D modeling codes. In this paper, we present an alternative approach using the Light Gradient Boosting (LightGBM) machine learning algorithm. The Medium Energy electRon fLux In Earth's outer radiatioN belt (MERLIN) model takes as input the satellite position, a combination of geomagnetic indices and solar wind parameters including the time history of velocity, and does not use persistence. MERLIN is trained on >15 years of the GPS electron flux data and tested on more than 1.5 years of measurements. Tenfold cross validation yields that the model predicts the MEO radiation environment well, both in terms of dynamics and amplitudes o f flux. Evaluation on the test set shows high correlation between the predicted and observed electron flux (0.8) and low values of absolute error. The MERLIN model can have wide space weather applications, providing information for the scientific community in the form of radiation belts reconstructions, as well as industry for satellite mission design, nowcast of the MEO environment, and surface charging analysis. |
| format | Article |
| id | doaj-art-d0845aa91a3f42c583736c2bdf5ef655 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2020-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-d0845aa91a3f42c583736c2bdf5ef6552025-01-14T16:30:47ZengWileySpace Weather1542-73902020-11-011811n/an/a10.1029/2020SW002532Medium Energy Electron Flux in Earth's Outer Radiation Belt (MERLIN): A Machine Learning ModelA. G. Smirnov0M. Berrendorf1Y. Y. Shprits2E. A. Kronberg3H. J. Allison4N. A. Aseev5I. S. Zhelavskaya6S. K. Morley7G. D. Reeves8M. R. Carver9F. Effenberger10Helmholtz‐Centre Potsdam ‐ GFZ German Research Centre for Geosciences Potsdam GermanyDepartment of Database Systems and Data Mining Ludwig‐Maximilians University of Munich Munich GermanyHelmholtz‐Centre Potsdam ‐ GFZ German Research Centre for Geosciences Potsdam GermanyDepartment of Earth and Environmental Sciences Ludwig Maximilians University of Munich Munich GermanyHelmholtz‐Centre Potsdam ‐ GFZ German Research Centre for Geosciences Potsdam GermanyHelmholtz‐Centre Potsdam ‐ GFZ German Research Centre for Geosciences Potsdam GermanyHelmholtz‐Centre Potsdam ‐ GFZ German Research Centre for Geosciences Potsdam GermanySpace Science and Applications Los Alamos National Laboratory Los Alamos NM USASpace Science and Applications Los Alamos National Laboratory Los Alamos NM USASpace Science and Applications Los Alamos National Laboratory Los Alamos NM USAHelmholtz‐Centre Potsdam ‐ GFZ German Research Centre for Geosciences Potsdam GermanyAbstract The radiation belts of the Earth, filled with energetic electrons, comprise complex and dynamic systems that pose a significant threat to satellite operation. While various models of electron flux both for low and relativistic energies have been developed, the behavior of medium energy (120–600 keV) electrons, especially in the MEO region, remains poorly quantified. At these energies, electrons are driven by both convective and diffusive transport, and their prediction usually requires sophisticated 4D modeling codes. In this paper, we present an alternative approach using the Light Gradient Boosting (LightGBM) machine learning algorithm. The Medium Energy electRon fLux In Earth's outer radiatioN belt (MERLIN) model takes as input the satellite position, a combination of geomagnetic indices and solar wind parameters including the time history of velocity, and does not use persistence. MERLIN is trained on >15 years of the GPS electron flux data and tested on more than 1.5 years of measurements. Tenfold cross validation yields that the model predicts the MEO radiation environment well, both in terms of dynamics and amplitudes o f flux. Evaluation on the test set shows high correlation between the predicted and observed electron flux (0.8) and low values of absolute error. The MERLIN model can have wide space weather applications, providing information for the scientific community in the form of radiation belts reconstructions, as well as industry for satellite mission design, nowcast of the MEO environment, and surface charging analysis.https://doi.org/10.1029/2020SW002532machine learningradiation beltselectron fluxempirical modelingmagnetosphereelectrons |
| spellingShingle | A. G. Smirnov M. Berrendorf Y. Y. Shprits E. A. Kronberg H. J. Allison N. A. Aseev I. S. Zhelavskaya S. K. Morley G. D. Reeves M. R. Carver F. Effenberger Medium Energy Electron Flux in Earth's Outer Radiation Belt (MERLIN): A Machine Learning Model Space Weather machine learning radiation belts electron flux empirical modeling magnetosphere electrons |
| title | Medium Energy Electron Flux in Earth's Outer Radiation Belt (MERLIN): A Machine Learning Model |
| title_full | Medium Energy Electron Flux in Earth's Outer Radiation Belt (MERLIN): A Machine Learning Model |
| title_fullStr | Medium Energy Electron Flux in Earth's Outer Radiation Belt (MERLIN): A Machine Learning Model |
| title_full_unstemmed | Medium Energy Electron Flux in Earth's Outer Radiation Belt (MERLIN): A Machine Learning Model |
| title_short | Medium Energy Electron Flux in Earth's Outer Radiation Belt (MERLIN): A Machine Learning Model |
| title_sort | medium energy electron flux in earth s outer radiation belt merlin a machine learning model |
| topic | machine learning radiation belts electron flux empirical modeling magnetosphere electrons |
| url | https://doi.org/10.1029/2020SW002532 |
| work_keys_str_mv | AT agsmirnov mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel AT mberrendorf mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel AT yyshprits mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel AT eakronberg mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel AT hjallison mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel AT naaseev mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel AT iszhelavskaya mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel AT skmorley mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel AT gdreeves mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel AT mrcarver mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel AT feffenberger mediumenergyelectronfluxinearthsouterradiationbeltmerlinamachinelearningmodel |