Journal article
Imbalanced Regressive Neural Network Model for Whistler‐Mode Hiss Waves: Spatial and Temporal Evolution
Journal of geophysical research. Space physics, Vol.129(8), e2024JA032761
08/2024
DOI: 10.1029/2024JA032761
Abstract
Abstract Whistler‐mode hiss waves are crucial to the dynamics of Earth's radiation belts, particularly in the scattering and loss of energetic electrons and forming the slot region between the inner and outer belts. The generation of hiss waves involves multiple potential mechanisms, which are under active research. Understanding the role of hiss waves in radiation belt dynamics and their generation mechanisms requires analyzing their temporal and spatial evolutions, especially for strong hiss waves. Therefore, we developed an Imbalanced Regressive Neural Network (IR‐NN) model for predicting hiss amplitudes. This model addresses the challenge posed by the data imbalance of the hiss data set, which consists of predominantly quiet‐time background samples and fewer but significant active‐time intense hiss samples. Notably, the IR‐NN hiss model excels in predicting strong hiss waves (>100 pT ). We investigate the temporal and spatial evolution of hiss wave during a geomagnetic storm on 24–27 October 2017. We show that hiss waves occur within the nominal plasmapause, and follow its dynamically evolving shape. They exhibit intensifications with 1 and 2 hr timescale similar to substorms but with a noticeable time delay. The intensifications begin near dawn and progress toward noon and afternoon. During the storm recovery phase, hiss intensifications may occur in the plume. Additionally, we observe no significant latitudinal dependence of the hiss waves within |MLAT| < 20°. In addition to describing the spatiotemporal evolution of hiss waves, this study highlights the importance of imbalanced regressive methods, given the prevalence of imbalanced data sets in space physics and other real‐world applications.
Plain Language Summary Whistler‐mode hiss waves play a crucial role in understanding the dynamics of Earth's radiation belts, particularly scattering and loss of energetic electrons and the formation of the slot region. The underlying generation mechanisms of hiss wave sources remain an active area of research, which needs to quantify the global evolution of these waves, especially powerful ones. We developed an Imbalanced Regressive Neural Network (IR‐NN) model, which excels at accurately predicting strong hiss wave activity, that is of particular interest in radiation belt studies. We analyzed the evolution of hiss waves during a geomagnetically active period in October 2017. We found that these waves predominantly occur within the plasmapause boundary and exhibit dynamics that follow the plasmapause's changes. These waves strengthen on timescales similar to those of magnetospheric substorms, with a slight delay, and move to different local times during different phases of the storm. These waves maintain uniform intensity across low to mid‐latitudes. This study underlines the importance of imbalanced regressive methods in handling imbalanced data sets, a common challenge in space physics and related physical science fields. This approach is not only significant for advancing our understanding of space weather phenomena but also has broader implications in other areas.
Key Points An imbalanced regressive neural network model of hiss amplitude developed that predicts quiet‐time background and active‐time intense waves Hiss waves are well organized inside the plasmapause and follow its dynamic shape, evolving from dawn toward later local time during a storm Modeled hiss evolution correlates with chorus, supporting the hypothesis that hiss is generated by evolving chorus waves
Details
- Title: Subtitle
- Imbalanced Regressive Neural Network Model for Whistler‐Mode Hiss Waves: Spatial and Temporal Evolution
- Creators
- Xiangning Chu - Laboratory for Atmospheric and Space PhysicsJacob Bortnik - University of California, Los AngelesXiao‐Chen Shen - Boston UniversityQianli Ma - University of California, Los AngelesWen Li - Boston UniversityDonglai Ma - University of California, Los AngelesDavid Malaspina - Laboratory for Atmospheric and Space PhysicsSheng Huang - Boston UniversityDavid P. Hartley - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Journal of geophysical research. Space physics, Vol.129(8), e2024JA032761
- DOI
- 10.1029/2024JA032761
- ISSN
- 2169-9380
- eISSN
- 2169-9402
- Publisher
- AMER GEOPHYSICAL UNION
- Grant note
- NASA ECIP: 80NSSC19K0911, 80NSSC20K0196, 80NSSC22K1023, 80NSSC20K1325, 80NSSC23K0096, 80NSSC18K1227 NSF: AGS-2247255, AGS-2025706, AGS-1847818, AGS-2225445, AGS-2247774 AFOSR YIP: FA9550-23-1-0359 University of Colorado Boulder under NASA: 80NSSC22K1023, 80NSSC20K1580 NASA: 80NSSC24K0266, 80NSSC24K0239, 80NSSC20K0698, 80NSSC24K0572, 80NSSC20K1324, 80NSSC21K0519 FINESST: 80NSSC21K1385 Extreme Science and Engineering Discovery Environment (XSEDE) Bridges GPU at the PSC through allocation: TG-PHY190033
XC would like to thank grant NASA ECIP 80NSSC19K0911, 80NSSC20K0196, 80NSSC22K1023, 80NSSC20K1325, 80NSSC23K0096, 80NSSC18K1227, NSF Grant AGS-2247255, and AFOSR YIP FA9550-23-1-0359. In addition, JB acknowledges support from subgrants to the University of California, Los Angeles, from the University of Colorado Boulder under NASA Prime Grant 80NSSC20K1580, and 80NSSC22K1023, and NSF award AGS-2025706. WL, XS, and QM acknowledge NASA Grants 80NSSC24K0266, 80NSSC24K0239, 80NSSC20K0698, 80NSSC24K0572, as well as the NSF Grants AGS-1847818, AGS-2225445, and AGS-2247774. DPH acknowledges support from NASA Grants 80NSSC20K1324 and 80NSSC21K0519. SH would like to acknowledge the FINESST Grant 80NSSC21K1385. This work used Extreme Science and Engineering Discovery Environment (XSEDE) Bridges GPU at the PSC through allocation TG-PHY190033.
- Language
- English
- Date published
- 08/2024
- Academic Unit
- Physics and Astronomy
- Record Identifier
- 9984696863402771
Metrics
58 Record Views