A machine-learning-based electron density (MLED) model in the inner magnetosphere

作     者：QingHua Zhou YunXiang Chen FuLiang Xiao Sai Zhang Si Liu Chang Yang YiHua He ZhongLei Gao QingHua Zhou;YunXiang Chen;FuLiang Xiao;Sai Zhang;Si Liu;Chang Yang;YiHua He;ZhongLei Gao

作者机构：School of Physics and Electronic SciencesChangsha University of Science and TechnologyChangsha 410114China Hunan Provincial Key Laboratory of Flexible Electronic Materials Genome EngineeringChangsha University of Science and TechnologyChangsha 410114China 

出 版 物：《Earth and Planetary Physics》 (地球与行星物理（英文版）)

年 卷 期：2022年第6卷第4期

页      面：350-358页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 070802[理学-空间物理学] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 0708[理学-地球物理学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：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 Foundation of Education Bureau of Hunan Province for Distinguished Young Scientists 20B004 

主　　题：background electron density inner magnetosphere machine learning Van Allen Probes observation 

摘      要：Plasma density is an important factor in determining wave-particle interactions in the *** 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,*** MLED model is a physics-based nonlinear network that employs fundamental physical principles to describe variations of electron *** predicts the plasmapause location under different geomagnetic conditions,and models separately the electron densities of the plasmasphere and of the *** 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 *** model gives explicit expressions with few parameters and describes the associations of electron density with geomagnetic activity,solar cycle,and seasonal *** various geomagnetic conditions,the electron densities calculated by this model agree well with empirical observations and provide a good description of plasmapause *** 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.