
Citation: | Zhou, Q. H., Chen, Y. X., Xiao, F. L., Zhang, S., Liu, S., Yang, C., He, Y. H., and Gao, Z. L. (2022). A machine-learning-based electron density (MLED) model in the inner magnetosphere. Earth Planet. Phys., 6(4), 350–358. DOI: 10.26464/epp2022036 |
Plasma density is an important factor in determining wave-particle interactions in the magnetosphere. We develop a machine-learning-based electron density (MLED) model in the inner magnetosphere using electron density data from Van Allen Probes between September 25, 2012 and August 30, 2019. This MLED model is a physics-based nonlinear network that employs fundamental physical principles to describe variations of electron density. It predicts the plasmapause location under different geomagnetic conditions, and models separately the electron densities of the plasmasphere and of the trough. We train the model using gradient descent and backpropagation algorithms, which are widely used to deal effectively with nonlinear relationships among physical quantities in space plasma environments. The model gives explicit expressions with few parameters and describes the associations of electron density with geomagnetic activity, solar cycle, and seasonal effects. Under various geomagnetic conditions, the electron densities calculated by this model agree well with empirical observations and provide a good description of plasmapause movement. This MLED model, which can be easily incorporated into previously developed radiation belt models, promises to be very helpful in modeling and improving forecasting of radiation belt electron dynamics.
The background electron density can affect the propagation and instability of electromagnetic waves in the magnetosphere (e.g. Chen LJ et al., 2009; Xiao FL et al., 2013; Guo MY et al., 2020; Guan CY et al., 2020; Sauer K et al., 2020). The plasmasphere is composed of low-energy particles, forming a sphere-like reservoir of very cold (~1 eV), fairly dense plasma (~50−104 cm−3) that co-rotates with the Earth. Recently, the method for Extreme Ultraviolet (EUV) image reconstruction of the plasmasphere was improved by Huang Y et al. (2021). The low-density region outside the plasmasphere is called the trough. The boundary between the plasmasphere and trough regions is the “plasmapause”. The plasmapause varies with magnetic local time (MLT) and geomagnetic activity (Chappell, 1972; Carpenter and Anderson, 1992; Larsen et al., 2007; Fu HS et al., 2010a). Observations (e.g. Goldstein et al., 2004; Darrouzet et al., 2008; Goldstein et al., 2014) have shown that the enhanced convection electric field during geomagnetic activity leads to erosion of the plasmasphere and formation of a high-density plume in the afternoon sector. In the early stage of its formation, the plasmaspheric plume is generally broad in MLT. It co-rotates with the Earth and becomes narrower as time goes on. In addition, the existence of density troughs inside the main body of the plasmasphere has been confirmed by observation (Fu HS et al., 2010b). Whistler-mode chorus mainly appears in the plasmatrough (Meredith et al., 2012); whistler-mode hiss appears mainly in the plasmasphere (Thorne et al., 1973; Wang JZ et al., 2020). Electrostatic electron cyclotron harmonic waves tend to be generated in the lower (upper) half of harmonic bands in the lower (higher) density region (Zhou QH et al., 2017). In addition, the diffusion coefficients controlling wave-particle interactions are closely related to the background density. Acceleration (scattering loss) of particles by waves generally occurs in the lower (higher) density region (e.g. Xiao FL et al., 2009, 2010, 2015; He JB et al., 2021; Yang C et al., 2021).
Direct measurement of electron density is a challenging task. It can be derived from spacecraft potentials (Escoubet et al., 1997) or, alternativelty, from the upper hybrid resonance frequency fuh (Kurth et al., 2015). Van Allen Probes running in the inner magnetosphere have provided measurements of electron density (inferred from fuh) that are more reliable than previous approaches. However, these in-situ measurements detect only the local electron density where the spacecraft is located. A number of empirical models have been developed to obtain a global distribution of the electron density in the inner magnetosphere under various magnetospheric conditions. The model by Carpenter and Anderson (1992) is derived from ISEE-1 data and valid for L shells between 2.25 and 8. The model presents separate empirical functions for the equatorial densities of the plasmaspheric and the trough regions. In this model the trough density depends on L shell; the plasmaspheric density depends on L shell, the long-term solar cycle, and seasonal effects. The plasmapause location is determined by the maximum geomagnetic activity index (Kp) in the preceding 24 hours. The Global Core Plasma Model (GCPM) (Gallagher et al., 2000) is an improvement of several previous models (Carpenter and Anderson, 1992; Gallagher et al., 1995). It incorporates densities of the plasmasphere, the trough, and the polar cap, and considers the influences of the Kp index and MLT on the plasmapause location. The model by Sheeley et al. (2001) is developed from density data from the Combined Release and Radiation Effects Satellite (CRRES). The plasmasphere density is a function of L shell; the trough density is a function of L shell and MLT, both of which are independent of geomagnetic activity. The model is valid for L shells between 3 and 7. Bortnik et al. (2016) developed neural network models for predicting the inner magnetospheric state. They then have published 2D and 3D neural network models for electron density based on data from Time History of Events and Macroscale Interactions during Substorms (THEMIS) Probes (Chu XN et al., 2017a, b; Bortnik et al., 2018). Zhelavskaya et al. (2017) have presented a neural network model for electron density based on EMFISIS data from the Van Allen Probes mission. However, these neural network models have not provided explicit expressions and parameters.
We construct a physics-based nonlinear network to describe the dynamic and nonlinear relationships between electron density and geomagnetic activity levels, solar cycle effects, and seasonal effects. Using data from Van Allen Probes mission during the period from September 25, 2012 to August 30, 2019, we perform machine learning with gradient descent and backpropagation algorithms to find the optimal parameters of the density model. We shall present explicit expressions with few parameters, which can be used straightforwardly by the radiation belt community.
The high-frequency receiver (HFR) of the Electric and Magnetic Field Instrument Suite and Integrated Science (EMFISIS) instrumentation suite on board the Van Allen Probes mission measures electric components of plasma waves in the frequency range of 10 to 500 kHz, and provides electron density (N) data inferred from fuh. The density data are available from September 25, 2012 to August 30, 2019. We combined them with MagEphem data from Van Allen Probes and from OMNI (Operating Missions as Nodes on the Internet). Each data sample contains N, Kp index, SYM-H index, the 13-month-average sunspot number (
latitude to form a data set (1,017,586 observations in total). Samples in the data set are binned as a function of L in steps of 0.5 L and MLT in an interval of 1 h. We plot the corresponding global distribution of the samples in Figure 1. The number of samples increases as L increases. In the region of 1.1 < L < 2.5, there are fewer than 5000 samples in each bin. In the region of 5.0 < L < 6.0, more than 8000 samples are obtained in each bin. Samples occur most frequently from the dusk-to-midnight side. The bin with the most samples (20,000 samples) is located in the region of L = 5.5−6.0 and 15 < MLT < 17. O’Brien and Moldwin (2003) investigated the role of various geomagnetic indices in modeling the plasmapause location. They found that the recent minimum Dst index provides a better model than the maximum Kp index, which is used in GCPM. Therefore, we use the minimum SYM-H in the preceding 24 hours (SYM-Hm24) to represent the geomagnetic activity level. Figures 1b−1d show that the global distribution of samples under various geomagnetic activities is basically the same. The number of samples during SYM-Hm24 > −30 nT, −50 nT < SYM-Hm24 ≤ −30 nT and SYM-Hm24 ≤ −50 nT are 791,340, 147,517 and 78,729, respectively. Under these geomagnetic activity conditions, the orbits of Van Allen Probes have good statistical coverage for 1.1 < L < 6.0 and all magnetic local times near the equator.
For the plasmaspheric density, we adopt equations similar to the GCPM (Gallagher et al., 2000):
Nps=10g⋅h−1, |
(1) |
g=(k1L+k2)+k3[(cos2π(DoY+9)365+k4cos4π(DoY+9)365)+k5¯R+k6]e−(L−2)1.5, |
(2) |
h=[1+(LLpp)2(a9−1)](a91−a9), |
(3) |
where Lpp is the location of the midpoint of the plasmapause and a9 controls the plasmapause gradient. Both terms are associated with Q = log10|SYM-Hm24 |:
Lpp=(b1Q+b2)[1+e(−1.5x2+0.08x−0.7)], |
(4) |
a9=(b3Q+b4), |
(5) |
where
b1=k7cos(MLT12π)+k8, |
(6) |
b2=k9cos(MLT12π)+k10, |
(7) |
b3=k11cos(MLT12π)+k12, |
(8) |
b4=k13cos(MLT12π)+k14, |
(9) |
x={|MLT−ΦB|π/12,|MLT−ΦB|<12,(24−|MLT−ΦB|)π/12,|MLT−ΦB|≥12, |
(10) |
ΦB=k15Q+k16+k17. |
(11) |
For the trough, the variation of density with L shell and MLT is described following the form of the trough model proposed by (Sheeley et al., 2001):
Ntr=k18(3L)4.0+k19(3L)3.5cos({MLT−[7.7(3L)2+12]}π12). |
(12) |
By integrating plasmaspheric and trough densities, the electron density is represented by:
N=u1Ntr+u2Nps, |
(13) |
where u1 and u2 are functions that connect one regional description to another:
u1=0.5tanh[3.4534(L−Lpp)0.1]+0.5, |
(14) |
u2=0.5tanh[−3.4534(L−Lpp)0.1]+0.5. |
(15) |
It should be mentioned that the electron density varies with season by a cycle of 365 days and with MLT by a cycle of 24 hours. Since both cycles are symmetrically distributed, previous studies (Gallagher et al., 2000; Sheeley et al., 2001) have used cosine functions to describe the density variation with DoY and MLT. Therefore, we choose similar expressions of density variation with DoY and MLT. Meanwhile, some parameter values in Equations (1)−(15) can reasonably describe the density variation with season and MLT. To reduce the computational time and the number of parameters that need to be fitted, the values of these parameters are adopted directly from those previous studies (Gallagher et al., 2000; Sheeley et al., 2001).
We obtain optimal parameters of the density model (k1–k19) using standard methods for optimizing classical neural networks, i.e., gradient descent and backpropagation algorithms (Rumelhart et al., 1986; Hecht-Nielsen, 1989). We use the mean square error (MSE) as the cost function:
J(k1,k2,⋯,k19)=MSE=1nn∑i=1(ˆN(i)−N(i))2, |
(16) |
where n is the sample size of the training data set,and
Figure 2 shows the constructed network of neuron-like units according to Equations (1)−(15). This is a nonlinear network because these equations are nonlinear. The orange nodes represent the input parameters of the density model. The intermediate variables and the output of the model are represented by the green nodes. We follow the blue arrows to calculate the density and cost function of the model. The derivatives of the cost function with respect to the parameter
R2a=1−n−1n−p−1∑i(ˆNi−Ni)2∑i(Ni−¯N)2, |
(17) |
where
In order to avoid the contingency of results caused by the random division of the data set, 5-fold cross-validation (Ojala and Garriga, 2009) is used. The dataset is divided into five blocks randomly and evenly, without overlap between any of them. We perform five training sessions, taking one block in each turn as the test set and the remaining four blocks as the training set. One thousand iterations are performed in each training session; the mini-batch of each iteration is 200 samples randomly selected from the training data set. We obtain five different models from the five training sessions and calculate
Table 1 lists the optimal values of parameters in Equations (1)−(12). Figure 3 shows the regression of the modeled (Nmodel) and observed (Nobs) electron densities for various data sets. The classes of each dataset and the corresponding correlation coefficients (R) are shown in the panel headers. The data points are essentially distributed close to the dashed line representing the perfect fit, suggesting that the MLED model fits the observations well. The samples near the perfect fit line in Figure 3 are much larger than those away from the perfect fit line. The correlation of observations with MLED predictions is greater than 0.87 in all three datasets. Thus, the MLED model appears to offer promising prediction performance. The correlation coefficient on the test dataset is 0.90, implying that the MLED model has good generalizability. In machine learning tasks, overfitting may occur when the model is too complex and the metrics of the training set are much better than those of the test set. The concise network used here avoids overfitting. For such concise networks, it is possible that the metrics of the test set are slightly higher than those of the training set, as shown in Figure 3.
Parameter | Value | Parameter | Value | |
k1 | −0.43 | k11 | 2.1726 | |
k2 | 4.4 | k12 | −1.5138 | |
k3 | 0.09867 | k13 | −7.9149 | |
k4 | −0.2555 | k14 | 44.2847 | |
k5 | 0.0022 | k15 | 14.4557 | |
k6 | −1.956 | k16 | 1.2235 | |
k7 | 0.015 | k17 | 11.5 | |
k8 | −1.5226 | k18 | 187.7 | |
k9 | 0.0319 | k19 | 88.2 | |
k10 | 5.7689 |
In Table 2 we present the
Training | Test | |||||
MLED | GCPM | MLED | GCPM | |||
All samples | R2a | 0.7383 | −0.2282 | 0.7702 | 0.1126 | |
RMSE | 259.0 | 561.1 | 242.9 | 477.3 | ||
SYM-Hm24 > −30 nT | R2a | 0.7485 | −0.1423 | 0.8085 | 0.3448 | |
RMSE | 254.7 | 542.9 | 227.9 | 450.8 | ||
−50 nT < SYM-Hm24 ≤ −30 nT | R2a | 0.7075 | −0.4212 | 0.7661 | 0.1904 | |
RMSE | 266.2 | 586.7 | 242.3 | 421.6 | ||
SYM-Hm24 ≤ −50 nT | R2a | 0.5769 | −1.5331 | 0.5666 | −1.2918 | |
RMSE | 301.8 | 738.4 | 291.7 | 670.8 |
We extracted samples from the data set at midnight (MLT = 0), dawn (MLT = 6), noon (MLT = 12) and dusk (MLT = 18) during different levels of geomagnetic activity. We use the measured data (L, MLT,
The
MLT = 0 | MLT = 6 | MLT = 12 | MLT = 18 | ||
SYM-Hm24 > −30 nT | MLED | 0.7267 | 0.7444 | 0.7875 | 0.8102 |
GCPM | −0.6418 | −0.4475 | 0.2170 | 0.3847 | |
−50 nT < SYM-Hm24 ≤ −30 nT | MLED | 0.6873 | 0.7685 | 0.6784 | 0.6994 |
GCPM | −0.9493 | −1.1429 | 0.1843 | 0.3661 | |
SYM-Hm24 ≤ −50 nT | MLED | −0.7856 | 0.4437 | 0.4910 | 0.6311 |
GCPM | −2.2801 | −2.9358 | −2.0681 | −0.2622 |
MLT = 0 | MLT = 6 | MLT = 12 | MLT = 18 | ||
SYM-Hm24 > −30 nT | MLED | 291.6 | 223.2 | 231.9 | 215.4 |
GCPM | 714.6 | 531.2 | 445.2 | 387.9 | |
−50 nT < SYM-Hm24 ≤ −30 nT | MLED | 304.5 | 305.6 | 257.8 | 211.8 |
GCPM | 760.3 | 929.8 | 410.6 | 307.6 | |
SYM-Hm24 ≤ −50 nT | MLED | 213.2 | 417.1 | 320.3 | 231.9 |
GCPM | 834.0 | 1109 | 786.3 | 428.9 |
Figure 6 shows the distribution of the relative error as a function of L for MLED and GCPM models under different geomagnetic activities. The mean relative errors and standard deviations are illustrated as bar plots. The relative error is defined as the ratio of the absolute error of the modeled value to the observed value: (Nmodel − Nobs)/Nobs. The standard deviation is used to estimate the uncertainty of the density model predictions. The absolute values of mean relative errors of the MLED model are less than ~0.3 and significantly smaller than those of the GCPM model at different L shells. Figures 6d−6f further confirm the results of Figure 5 that the GCPM model produces overestimates at lower L shells and underestimates at higher L shells. The MLED model can be incorporated into the previously developed radiation belt models (e.g. Glauert and Horne, 2005; Xiao FL et al., 2009, 2010; Su ZP et al., 2010; Shprits et al., 2015) to better forecast the dynamic evolution of energetic electrons in the radiation belt.
During the period from September 25, 2012 to August 30, 2019, Van Allen Probes covered all magnetic local times in the low latitude region of L = 1.1 − 6.0 and provided a good opportunity to measure electron density on the global scale. We develop a machine-learning-based model of the equatorial electron density (MLED) in the inner magnetosphere based on density data from the Van Allen Probes mission. This MLED model is a physics-based nonlinear network. Gradient descent and backpropagation algorithms are used to find the optimal parameters of the nonlinear network. This approach can efficiently treat nonlinear relationships among physical quantities in space plasma environments. Compared to recently developed neural network density models (Chu XN et al., 2017a, b; Zhelavskaya et al., 2017; Bortnik et al., 2018), this MLED model provides explicit expressions with very few parameters and is therefore easily described and deployed.
The MLED model describes the variation of electron density in the inner magnetosphere as a function of L, MLT, SYM-H index, DoY, and
It should be mentioned that the MLED model adopts a concise network structure with the input parameters L, MLT,
This work is supported by the National Natural Science Foundation of China grants 42074198, 41774194, 41974212 and 42004141, Natural Science Foundation of Hunan Province 2021JJ20010, Science and Technology Innovation Program of Hunan Province 2021RC3098, and Foundation of Education Bureau of Hunan Province for Distinguished Young Scientists 20B004. All the Van Allen Probes data are publicly available at https://cdaweb.gsfc.nasa.gov/pub/data/rbsp/. The OMNI data are obtained online (https://spdf.gsfc.nasa.gov/pub/data/omni/).
Bortnik, J., Li, W., Thorne, R. M., and Angelopoulos, V. (2016). A unified approach to inner magnetospheric state prediction. J. Geophys. Res.:Space Phys., 121(3), 2423–2430. https://doi.org/10.1002/2015JA021733
|
Bortnik, J., Chu, X. N., Ma, Q. L., Li, W., Zhang, X. J., Thorne, R. M., Angelopoulos, V., Denton, R. E., Kletzing, C. A., … Baker, D. N. (2018). Artificial neural networks for determining magnetospheric conditions. In E. Camporeale, et al. (Eds.), Machine Learning Techniques for Space Weather (pp. 279-300). Amsterdam, Netherlands: Elsevier.
|
Carpenter, D. L., and Anderson, R. R. (1992). An ISEE/whistler model of equatorial electron density in the magnetosphere. J. Geophys. Res.:Space Phys., 97(A2), 1097–1108. https://doi.org/10.1029/91JA01548
|
Chappell, C. R. (1972). Recent satellite measurements of the morphology and dynamics of the plasmasphere. Rev. Geophys., 10(4), 951–979. https://doi.org/10.1029/RG010i004p00951
|
Chen, L. J., Thorne, R. M., and Horne, R. B. (2009). Simulation of EMIC wave excitation in a model magnetosphere including structured high-density plumes. J. Geophys. Res.:Space Phys., 114(A7), A07221. https://doi.org/10.1029/2009JA014204
|
Chu, X. N., Bortnik, J., Li, W., Ma, Q., Angelopoulos, V., and Thorne, R. M. (2017a). Erosion and refilling of the plasmasphere during a geomagnetic storm modeled by a neural network. J. Geophys. Res.:Space Phys., 122(7), 7118–7129. https://doi.org/10.1002/2017JA023948
|
Chu, X. N., Bortnik, J., Li, W., Ma, Q. L., Denton, R., Yue, C., Angelopoulos, V., Thorne, R. M., Darrouzet, F., … Menietti, J. (2017b). A neural network model of three-dimensional dynamic electron density in the inner magnetosphere. J. Geophys. Res.:Space Phys., 122(9), 9183–9197. https://doi.org/10.1002/2017JA024464
|
Darrouzet, F., De Keyser, J., Décréau, P. M. E., El Lemdani-Mazouz, F., and Vallières, X. (2008). Statistical analysis of plasmaspheric plumes with Cluster/WHISPER observations. Ann. Geophys., 26(8), 2403–2417. https://doi.org/10.5194/angeo-26-2403-2008
|
Escoubet, C. P., Pedersen, A., Schmidt, R., and Lindqvist, P. A. (1997). Density in the magnetosphere inferred from ISEE 1 spacecraft potential. J. Geophys. Res.:Space Phys., 102(A8), 17595–17609. https://doi.org/10.1029/97JA00290
|
Fu, H. S., Tu, J., Song, P., Cao, J. B., Reinisch, B. W., and Yang, B. (2010a). The nightside-to-dayside evolution of the inner magnetosphere: Imager for Magnetopause-to-Aurora Global Exploration Radio Plasma Imager observations. J. Geophys. Res.:Space Phys., 115(A4), A04213. https://doi.org/10.1029/2009JA014668
|
Fu, H. S., Tu, J., Cao, J. B., Song, P., Reinisch, B. W., Gallagher, D. L., and Yang, B. (2010b). IMAGE and DMSP observations of a density trough inside the plasmasphere. J. Geophys. Res.:Space Phys., 115(A7), A07227. https://doi.org/10.1029/2009JA015104
|
Gallagher, D. L., Craven, P. D., Comfort, R. H., and Moore, T. E. (1995). On the azimuthal variation of core plasma in the equatorial magnetosphere. J. Geophys. Res.:Space Phys., 100(A12), 23597–23605. https://doi.org/10.1029/95JA02100
|
Gallagher, D. L., Craven, P. D., and Comfort, R. H. (2000). Global core plasma model. J. Geophys. Res.:Space Phys., 105(A8), 18819–18833. https://doi.org/10.1029/1999JA000241
|
Glauert, S. A., and Horne, R. B. (2005). Calculation of pitch angle and energy diffusion coefficients with the PADIE code. J. Geophys. Res.:Space Phys., 110(A4), A04206. https://doi.org/10.1029/2004JA010851
|
Goldstein, J., Sandel, B. R., Thomsen, M. F., Spasojević, M., and Reiff, P. H. (2004). Simultaneous remote sensing and in situ observations of plasmaspheric drainage plumes. J. Geophys. Res.:Space Phys., 109(A3), A03202. https://doi.org/10.1029/2003JA010281
|
Goldstein, J., Thomsen, M. F., and DeJong, A. (2014). In situ signatures of residual plasmaspheric plumes: Observations and simulation. J. Geophys. Res.:Space Phys., 119(6), 4706–4722. https://doi.org/10.1002/2014JA019953
|
Guan, C. Y., Shang, X. J., Xie, Y. Q., Yang, C., Zhang, S., Liu, S., and Xiao, F. L. (2020). Generation of simultaneous H+ and He+ band EMIC waves in the nightside radiation belt. Sci. China Technol. Sci., 63(11), 2369–2374. https://doi.org/10.1007/s11431-019-1545-6
|
Guo, M. Y., Zhou, Q. H., Xiao, F. L., Liu, S., He, Y. H., and Yang, C. (2020). Upward propagation of lightning-generated whistler waves into the radiation belts. Sci. China Technol. Sci., 63(2), 243–248. https://doi.org/10.1007/s11431-018-9486-9
|
He, J. B., Jin, Y. Y., Xiao, F. L., He, Z. G., Yang, C., Xie, Y. Q., He, Q., Wang, C. Z., Shang, X. J., … Zhang, S. (2021). The influence of various frequency chorus waves on electron dynamics in radiation belts. Sci. China Technol. Sci., 64(4), 890–897. https://doi.org/10.1007/s11431-020-1750-6
|
Hecht-Nielsen, R. (1989). Theory of the backpropagation neural network. In International 1989 Joint Conference on Neural Networks (pp. 593-605). Washington, DC, USA: IEEE.
|
Huang, Y., Dai, L., Wang, C., Xu, R. L., and Li, L. (2021). A new inversion method for reconstruction of plasmaspheric He+ density from EUV images. Earth Planet. Phys., 5(2), 218–222. https://doi.org/10.26464/epp2021020
|
Kurth, W. S., De Pascuale, S., Faden, J. B., Kletzing, C. A., Hospodarsky, G. B., Thaller, S., and Wygant, J. R. (2015). Electron densities inferred from plasma wave spectra obtained by the Waves instrument on Van Allen Probes. J. Geophys. Res.:Space Phys., 120(2), 904–914. https://doi.org/10.1002/2014JA020857
|
Larsen, B. A., Klumpar, D. M., and Gurgiolo, C. (2007). Correlation between plasmapause position and solar wind parameters. J. Atmos. Sol. -Terr. Phys., 69(3), 334–340. https://doi.org/10.1016/j.jastp.2006.06.017
|
Meredith, N. P., Horne, R. B., Sicard-Piet, A., Boscher, D., Yearby, K. H., Li, W., and Thorne, R. M. (2012). Global model of lower band and upper band chorus from multiple satellite observations. J. Geophys. Res.:Space Phys., 117(A10), A10225. https://doi.org/10.1029/2012JA017978
|
O’Brien, T. P., and Moldwin, M. B. (2003). Empirical plasmapause models from magnetic indices. Geophys. Res. Lett., 30(4), 1152. https://doi.org/10.1029/2002GL016007
|
Ojala, M., and Garriga, G. C. (2009). Permutation tests for studying classifier performance. In 2009 Ninth IEEE International Conference on Data Mining (pp. 908-913). Miami Beach, FL, USA: IEEE.
|
Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533–536. https://doi.org/10.1038/323533a0
|
Sauer, K., Baumgärtel, K., and Sydora, R. (2020). Gap formation around Ωe/2 and generation of low-band whistler waves by Landau-resonant electrons in the magnetosphere: Predictions from dispersion theory. Earth Planet. Phys., 4(2), 138–150. https://doi.org/10.26464/epp2020020
|
Sheeley, B. W., Moldwin, M. B., Rassoul, H. K., and Anderson, R. R. (2001). An empirical plasmasphere and trough density model: CRRES observations. J. Geophys. Res.:Space Phys., 106(A11), 25631–25641. https://doi.org/10.1029/2000JA000286
|
Shprits, Y. Y., Kellerman, A. C., Drozdov, A. Y., Spence, H. E., Reeves, G. D., and Baker, D. N. (2015). Combined convective and diffusive simulations: VERB-4D comparison with 17 March 2013 Van Allen Probes observations. Geophys. Res. Lett., 42(22), 9600–9608. https://doi.org/10.1002/2015GL065230
|
Su, Z. P., Xiao, F. L., Zheng, H. N., and Wang, S. (2010). STEERB: A three-dimensional code for storm-time evolution of electron radiation belt. J. Geophys. Res.:Space Phys., 115(A9), A09208. https://doi.org/10.1029/2009JA015210
|
Su, Z. P., Liu, N. G., Zheng, H. N., Wang, Y. M., and Wang, S. (2018). Multipoint observations of nightside plasmaspheric hiss generated by substorm-injected electrons. Geophys. Res. Lett., 45(20), 10921–10932. https://doi.org/10.1029/2018GL079927
|
Thorne, R. M., Smith, E. J., Burton, R. K., and Holzer, R. E. (1973). Plasmaspheric hiss. J. Geophys. Res., 78(10), 1581–1596. https://doi.org/10.1029/JA078i010p01581
|
Wang, J. Z., Zhu, Q., Gu, X. D., Fu, S., Guo, J. G., Zhang, X. X., Yi, J., Guo, Y. J., Ni, B. B., and Xiang, Z. (2020). An empirical model of the global distribution of plasmaspheric hiss based on Van Allen Probes EMFISIS measurements. Earth Planet. Phys., 4(3), 246–265. https://doi.org/10.26464/epp2020034
|
Xiao, F. L., Su, Z. P., Zheng, H. N., and Wang, S. (2009). Modeling of outer radiation belt electrons by multidimensional diffusion process. J. Geophys. Res.:Space Phys., 114(A3), A03201. https://doi.org/10.1029/2008JA013580
|
Xiao, F. L., Su, Z. P., Zheng, H. N., and Wang, S. (2010). Three-dimensional simulations of outer radiation belt electron dynamics including cross-diffusion terms. J. Geophys. Res.:Space Phys., 115(A5), A05216. https://doi.org/10.1029/2009JA014541
|
Xiao, F. L., Zhou, Q. H., He, Z. G., Yang, C., He, Y. H., and Tang, L. J. (2013). Magnetosonic wave instability by proton ring distributions: Simultaneous data and modeling. J. Geophys. Res.:Space Phys., 118(7), 4053–4058. https://doi.org/10.1002/jgra.50401
|
Xiao, F. L., Yang, C., Su, Z. P., Zhou, Q. H., He, Z. G., He, Y. H., Baker, D. N., Spence, H. E., Funsten, H. O., and Blake, J. B. (2015). Wave-driven butterfly distribution of Van Allen belt relativistic electrons. Nat. Commun., 6, 8590. https://doi.org/10.1038/ncomms9590
|
Yang, C., Wang, Z. Q., Xiao, F. L., He, Z. G., Xie, Y. Q., Zhang, S., He, Y. H., Liu, S., and Zhou, Q. H. (2021). Correlated observations linking loss of energetic protons to EMIC waves. Sci. China Technol. Sci., 65(1), 131–138. https://doi.org/10.1007/s11431-021-1882-x
|
Zhelavskaya, I. S., Shprits, Y. Y., and Spasojević, M. (2017). Empirical modeling of the plasmasphere dynamics using neural networks. J. Geophys. Res.:Space Phys., 122(11), 11227–11244. https://doi.org/10.1002/2017JA024406
|
Zhou, Q. H., Xiao, F. L., Yang, C., Liu, S., He, Y. H., Baker, D. N., Spence, H. E., Reeves, G. D., and Funsten, H. O. (2017). Generation of lower and upper bands of electrostatic electron cyclotron harmonic waves in the Van Allen radiation belts. Geophys. Res. Lett., 44(11), 5251–5258. https://doi.org/10.1002/2017GL073051
|
AoJun Ren, Jiang Yu, Jing Wang, ZuZheng Chen, XiaoMan Liu. 2025: Statistical analysis on the validity of the cold plasma approximation for chorus waves based on Van Allen Probe observations and their effects on radiation belt electrons. Earth and Planetary Physics, 9(1): 159-170. DOI: 10.26464/epp2024057 | |
LuHuai Jiao, Xin Ma, YuanNong Zhang, TaiFeng Jin, Song Fu, BinBin Ni. 2024: A statistical analysis of the Kappa-type energy spectrum distribution of radiation belt electrons observed by Van Allen Probes. Earth and Planetary Physics, 8(2): 368-375. DOI: 10.26464/epp2024001 | |
Mao Zhang, GaoPeng Lu, HaiLiang Huang, ZhengWei Cheng, YaZhou Chen, Steven A. Cummer, JiaYi Zheng, JiuHou Lei. 2023: Automatic recognition of tweek atmospherics and plasma diagnostics in the lower ionosphere with the machine learning method. Earth and Planetary Physics, 7(3): 407-413. DOI: 10.26464/epp2023039 | |
Zheng Xiang, BinBin Ni, YangXiZi Liu, XuDong Gu, Song Fu, Wei Xu, Xing Cao, Xin Ma, DeYu Guo, JunHu Dong, JingLe Hu. 2023: Modeling the energetic electron fluxes in the inner radiation belt based on a drift-source model. Earth and Planetary Physics, 7(1): 100-108. DOI: 10.26464/epp2023012 | |
ChaoLing Tang, Xu Wang, BinBin Ni, ZhengPeng Su, JiChun Zhang. 2022: The 600 keV electron injections in the Earth’s outer radiation belt: A statistical study. Earth and Planetary Physics, 6(2): 149-160. DOI: 10.26464/epp2022012 | |
PengCheng Zhou, William L. Ellsworth, HongFeng Yang, Yen Joe Tan, Gregory C. Beroza, MinHan Sheng, RiSheng Chu. 2021: Machine-learning-facilitated earthquake and anthropogenic source detections near the Weiyuan Shale Gas Blocks, Sichuan, China. Earth and Planetary Physics, 5(6): 501-519. DOI: 10.26464/epp2021053 | |
Wing Ching Jeremy Wong, JinPing Zi, HongFeng Yang, JinRong Su. 2021: Spatial-temporal evolution of injection-induced earthquakes in the Weiyuan Area determined by machine-learning phase picker and waveform cross-correlation. Earth and Planetary Physics, 5(6): 485-500. DOI: 10.26464/epp2021055 | |
JingZhi Wang, Qi Zhu, XuDong Gu, Song Fu, JianGuang Guo, XiaoXin Zhang, Juan Yi, YingJie Guo, BinBin Ni, Zheng Xiang. 2020: An empirical model of the global distribution of plasmaspheric hiss based on Van Allen Probes EMFISIS measurements. Earth and Planetary Physics, 4(3): 246-265. DOI: 10.26464/epp2020034 | |
XiongDong Yu, ZhiGang Yuan, ShiYong Huang, Fei Yao, Zheng Qiao, John R. Wygant, Herbert O. Funsten. 2019: Excitation of extremely low-frequency chorus emissions: The role of background plasma density. Earth and Planetary Physics, 3(1): 1-7. DOI: 10.26464/epp2019001 | |
Rui Yan, YiBing Guan, XuHui Shen, JianPing Huang, XueMin Zhang, Chao Liu, DaPeng Liu. 2018: The Langmuir Probe onboard CSES: data inversion analysis method and first results. Earth and Planetary Physics, 2(6): 479-488. DOI: 10.26464/epp2018046 |
1. | Dubyagin, S., Ganushkina, N., Sicard, A. et al. PEMEM Percentile: New Plasma Environment Specification Model for Surface Charging Risk Assessment. Journal of Geophysical Research: Space Physics, 2024, 129(2): e2023JA032026. DOI:10.1029/2023JA032026 | |
2. | Xu, X., Zhou, C. Effects of Cold Plasma on the Mode Conversion From Fast Magnetosonic Wave to Electromagnetic Ion Cyclotron Wave in the Inner Plasmasphere. Journal of Geophysical Research: Space Physics, 2023, 128(9): e2022JA031273. DOI:10.1029/2022JA031273 | |
3. | Ding, Y., Hu, J., Zhang, H. et al. Areal-time seismic intensity prediction model based on multi-parameter driven machine learning | [基于多参数驱动机器学习的实时地震烈度预测模型]. Acta Geophysica Sinica, 2023, 66(7): 2920-2932. DOI:10.6038/cjg2022P0883 | |
4. | Shan, W., Yan, F., Liu, H. et al. Recognition of HVDC transmission disturbance events in geomagnetic observation data based on deep neural network | [基于深度神经网络的地磁观测数据高压直流输电干扰事件识别]. Acta Geophysica Sinica, 2023, 66(4): 1575-1588. DOI:10.6038/cjg2022Q0110 | |
5. | Deng, Z., Xiao, F., Zhou, Q. et al. Direct Evidence for Auroral Kilometric Radiation Propagation Into Radiation Belts Based on Arase Spacecraft and Van Allen Probe B. Geophysical Research Letters, 2022, 49(19): e2022GL100860. DOI:10.1029/2022GL100860 |
Parameter | Value | Parameter | Value | |
k1 | −0.43 | k11 | 2.1726 | |
k2 | 4.4 | k12 | −1.5138 | |
k3 | 0.09867 | k13 | −7.9149 | |
k4 | −0.2555 | k14 | 44.2847 | |
k5 | 0.0022 | k15 | 14.4557 | |
k6 | −1.956 | k16 | 1.2235 | |
k7 | 0.015 | k17 | 11.5 | |
k8 | −1.5226 | k18 | 187.7 | |
k9 | 0.0319 | k19 | 88.2 | |
k10 | 5.7689 |
Training | Test | |||||
MLED | GCPM | MLED | GCPM | |||
All samples | R2a | 0.7383 | −0.2282 | 0.7702 | 0.1126 | |
RMSE | 259.0 | 561.1 | 242.9 | 477.3 | ||
SYM-Hm24 > −30 nT | R2a | 0.7485 | −0.1423 | 0.8085 | 0.3448 | |
RMSE | 254.7 | 542.9 | 227.9 | 450.8 | ||
−50 nT < SYM-Hm24 ≤ −30 nT | R2a | 0.7075 | −0.4212 | 0.7661 | 0.1904 | |
RMSE | 266.2 | 586.7 | 242.3 | 421.6 | ||
SYM-Hm24 ≤ −50 nT | R2a | 0.5769 | −1.5331 | 0.5666 | −1.2918 | |
RMSE | 301.8 | 738.4 | 291.7 | 670.8 |
MLT = 0 | MLT = 6 | MLT = 12 | MLT = 18 | ||
SYM-Hm24 > −30 nT | MLED | 0.7267 | 0.7444 | 0.7875 | 0.8102 |
GCPM | −0.6418 | −0.4475 | 0.2170 | 0.3847 | |
−50 nT < SYM-Hm24 ≤ −30 nT | MLED | 0.6873 | 0.7685 | 0.6784 | 0.6994 |
GCPM | −0.9493 | −1.1429 | 0.1843 | 0.3661 | |
SYM-Hm24 ≤ −50 nT | MLED | −0.7856 | 0.4437 | 0.4910 | 0.6311 |
GCPM | −2.2801 | −2.9358 | −2.0681 | −0.2622 |
MLT = 0 | MLT = 6 | MLT = 12 | MLT = 18 | ||
SYM-Hm24 > −30 nT | MLED | 291.6 | 223.2 | 231.9 | 215.4 |
GCPM | 714.6 | 531.2 | 445.2 | 387.9 | |
−50 nT < SYM-Hm24 ≤ −30 nT | MLED | 304.5 | 305.6 | 257.8 | 211.8 |
GCPM | 760.3 | 929.8 | 410.6 | 307.6 | |
SYM-Hm24 ≤ −50 nT | MLED | 213.2 | 417.1 | 320.3 | 231.9 |
GCPM | 834.0 | 1109 | 786.3 | 428.9 |