Identification of Controlling Geomagnetic and Solar Wind Factors for Magnetospheric Chorus Intensity Using Feature Selection Techniques

Guo, Yingjie; Ni, Binbin; Fu, Song; Wang, Dedong; Shprits, Y. Y.; Zhelavskaya, Irina; Feng, Maoyuan; Guo, Deyu

doi:10.1029/2021ja029926

Cited by 10 publications

(10 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, some assumptions and approximations could bring errors to our simulation results, such as the inaccuracy of the global chorus wave amplitudes deduced from the POES data, assumptions of background electron densities over different MLT sectors, and plasmapause location. Machine learning technique has been adopted to predict the global wave amplitude and plasma density, helping us evaluate the space weather dynamics with high accuracy (e.g., D. Guo, Fu, et al., 2021; Y. Guo et al., 2022; Zhelavskaya et al., 2021). The machine learning technique can be used in future simulation and forecast ultra‐relativistic electron fluxes in the Earth's radiation belts (Chu et al., 2021; D. Ma et al., 2022).…”

Section: Discussionmentioning

confidence: 99%

Three‐Dimensional Simulations of Ultra‐Relativistic Electron Acceleration During the 21 April 2017 Storm

Guo

Xiang

et al. 2023

JGR Space Physics

Self Cite

View full text Add to dashboard Cite

The acceleration mechanisms of ultra‐relativistic electrons (>∼5 MeV) have received more and more attention in the Van Allen Probes era. Both chorus waves and radial diffusion are considered capable of accelerating ultra‐relativistic electrons, and their roles in acceleration still under debate today. In this study, we present 3‐D simulations for evaluating the evolutions of ultra‐relativistic electron phase space density (PSD) during a weak storm on April 2017. Comparison of simulation results with observations suggests that local peaks in PSD profile of ultra‐relativistic electrons are generated by chorus waves, then smoothed and widened due to the transport of electrons from the peak to either side by radial diffusion. Chorus waves act dominantly in the acceleration of ultra‐relativistic electrons while radial diffusion assists. We also found that radial diffusion coefficient model of W. Liu et al. (2016, https://doi.org/10.1002/2015GL067398) is more suitable and reasonable than model of Brautigam and Albert (2000, https://doi.org/10.1029/1999JA900344) for 3‐D simulation of ultra‐relativistic electrons. A more accurate radial diffusion coefficient model is vital and demanded for quantitatively evaluating the contribution of these two mechanisms for ultra‐relativistic electrons acceleration in the future.

show abstract

Section: Discussionmentioning

confidence: 99%

Three‐Dimensional Simulations of Ultra‐Relativistic Electron Acceleration During the 21 April 2017 Storm

Guo

Xiang

et al. 2023

JGR Space Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The average wave amplitude is generally statistically modeled as a function of spatial location (L shell, MLT, and MLAT), and parameters used to categorize the chorus wave amplitude include solar wind parameters, geomagnetic indices, or a combination of these parameters (Agapitov et al., 2015, 2018; Aryan et al., 2014, 2016; W. Li et al., 2009, 2013a, 2013b, 2016; Meredith et al., 2012, 2018, 2020; Wang et al., 2019). Chorus waves have also been modeled using neural networks (Bortnik et al., 2018; Guo et al., 2022; Kim et al., 2015), performing better in errors than the statistically averaged models. However, these models generally fail to predict the correct intensity of strong chorus waves due to the highly imbalanced nature of the chorus database, which is discussed below.…”

Section: Introductionmentioning

confidence: 99%

“…Due to the imbalanced nature of the chorus waves, traditional statistical models cannot reproduce the time‐dependent variations of chorus waves, especially the strong wave amplitude (see discussion in Guo et al. (2022)). Therefore, for the first time, we developed a neural network model for the lower‐band (LB) chorus wave amplitude using an imbalanced regressive (IR) method, which can accurately predict both background noise and large wave amplitudes.…”

Section: Introductionmentioning

confidence: 99%

“…Li et al, , 2013aMeredith et al, 2012Meredith et al, , 2018Meredith et al, , 2020Wang et al, 2019). Chorus waves have also been modeled using neural networks (Bortnik et al, 2018;Guo et al, 2022;Kim et al, 2015), performing better in errors than the statistically averaged models. However, these models generally fail to predict the correct intensity of strong chorus waves due to the highly imbalanced nature of the chorus database, which is discussed below.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Distribution and Evolution of Chorus Waves Modeled by a Neural Network: The Importance of Imbalanced Regression

Chu,

Bortnik,

et al. 2023

Space Weather

View full text Add to dashboard Cite

Whistler‐mode chorus waves play an essential role in the acceleration and loss of energetic electrons in the Earth’s inner magnetosphere, with the more intense waves producing the most dramatic effects. However, it is challenging to predict the amplitude of strong chorus waves due to the imbalanced nature of the data set, that is, there are many more non‐chorus data points than strong chorus waves. Thus, traditional models usually underestimate chorus wave amplitudes significantly during active times. Using an imbalanced regressive (IR) method, we develop a neural network model of lower‐band (LB) chorus waves using 7‐year observations from the EMFISIS instrument onboard Van Allen Probes. The feature selection process suggests that the auroral electrojet index alone captures most of the variations of chorus waves. The large amplitude of strong chorus waves can be predicted for the first time. Furthermore, our model shows that the equatorial LB chorus’s spatiotemporal evolution is similar to the drift path of substorm‐injected electrons. We also show that the chorus waves have a peak amplitude at the equator in the source MLT near midnight, but toward noon, there is a local minimum in amplitude at the equator with two off‐equator amplitude peaks in both hemispheres, likely caused by the bifurcated drift paths of substorm injections on the dayside. The IR‐based chorus model will improve radiation belt prediction by providing chorus wave distributions, especially storm‐time strong chorus. Since data imbalance is ubiquitous and inherent in space physics and other physical systems, imbalanced regressive methods deserve more attention in space physics.

show abstract

“…Chu et al (2017aChu et al ( , 2017b and Zhelavskaya et al (2017) reconstructed dynamic plasma density models with multiple input streams (including solar wind parameters in addition to geomagnetic index time series) that captured the erosion and refilling of the plasmasphere. The ANN technique has also been successfully used to reconstruct radiation belt electron distributions (Chu et al, 2021;O'Brien, 2020 Ma et al, 2022;Landis et al, 2022;) and wave distributions (Bortnik et al, 2018;Guo et al, 2022).…”

mentioning

confidence: 99%

Modeling Ring Current Proton Fluxes Using Artificial Neural Network and Van Allen Probe Measurements

Bortnik

Chu

et al. 2023

Space Weather

View full text Add to dashboard Cite

Terrestrial ring current dynamics are a critical part of the near‐space environment, in that they directly drive geomagnetic field variations that control particle drifts, and define geomagnetic storms. The present study aims to specify a global and time‐varying distribution of ring current proton using geomagnetic indices and solar wind parameters with their history as input. We train an artificial neural network (ANN) model to reproduce proton fluxes measured by the Radiation Belt Storm Probes Ion Composition Experiment instrument onboard Van Allen Probes. By choosing optimal feature parameters and their history length, the model results show a high correlation and a small error between model specifications and satellite measurements. The modeled results well capture energy‐dependent proton dynamics in association with geomagnetic storms, including inward radial diffusion, acceleration and decay. Our ANN model produces proton fluxes with their corresponding 3D spatiotemporal variations, capturing the latitudinal distribution and local time asymmetry that are consistent with observations and that can further inform theory.

show abstract

Identification of Controlling Geomagnetic and Solar Wind Factors for Magnetospheric Chorus Intensity Using Feature Selection Techniques

Cited by 10 publications

References 54 publications

Three‐Dimensional Simulations of Ultra‐Relativistic Electron Acceleration During the 21 April 2017 Storm

Three‐Dimensional Simulations of Ultra‐Relativistic Electron Acceleration During the 21 April 2017 Storm

Distribution and Evolution of Chorus Waves Modeled by a Neural Network: The Importance of Imbalanced Regression

Modeling Ring Current Proton Fluxes Using Artificial Neural Network and Van Allen Probe Measurements

Contact Info

Product

Resources

About