Predicting SuperDARN cross polar cap potential by applying regression analysis and machine learning

Predicting SuperDARN cross polar cap potential by applying regression analysis and machine learning
复制标题

通过应用回归分析和机器学习预测 SuperDARN 跨极上限潜力

DOI:
10.1016/j.jastp.2019.105057
复制
发表时间:
2019-10
影响因子:
1.9
通讯作者:
Qiao Lei
Qiao Lei
中科院分区:
地球科学4区
文献类型:
--
作者:
Liu Erxiao;Hu Hongqiao;Liu Jianjun;Teng Xuyang;Qiao Lei

文献摘要

参考文献

相似文献

交叉极帽电位(CPCP)是表征高纬度电离层对流电动力特征的主要参数之一。在这项研究中,我们基于 1999 年至 2009 年的大型测量数据库,对超级双极光雷达网络 (SuperDARN) CPCP 及其与太阳风、行星际磁场 (IMF) 和地磁指数等各种参数的关系进行了全面研究。具体来说,考虑了IMF时钟角、IMF Bz、太阳风速、等离子体质子密度、AE指数、SymH指数和Dst指数。根据相关性结果,选择输入参数,并分别提出两种基于多元回归分析和反向传播人工神经网络(BP ANN)算法的CPCP模型。使用独立数据集对回归模型和BP ANN模型进行了验证,并测试了模型的准确性和稳定性。结果表明,实测值与模型值的均方根误差(RMSE)在3.7~6.7kV之间,线性相关系数接近或高于0.7。 ANN 模型比回归模型具有更好的性能。
The cross polar cap potential (CPCP) is one of the primary parameters characterizing the electrodynamic feature of the high latitude ionosphere convection. In this study, we perform a comprehensive investigation of the Super Dual Auroral Radar Network (SuperDARN) CPCP, based on a large database of measurements from 1999 to 2009, and its relationship with various parameters of the solar wind, interplanetary magnetic field (IMF) and geomagnetic indices. Specifically, the IMF clock angle, the IMF Bz, the solar wind velocity, the plasma proton density, AE index, SymH index and Dst index are under consideration. According to the results of the correlation, the input parameters are selected and two models of the CPCP based on the multivariate regression analysis and Back Propagation Artificial Neural Network (BP ANN) algorithm are proposed respectively. The regression and BP ANN models are validated and the accuracy as well as the stability of the models is tested by using independent datasets. The result shows that the root mean square error (RMSE) between the measured and the model values ranges from 3.7 to 6.7 kV and the linear correlation coefficients are close to, or above 0.7. The ANN model is shown to have a better performance than the regression model.
DOI: 10.1029/ja086ia09p07639
发表时间: 1981-09
影响因子: --
作者:
P. Reiff;R. Spiro;T. Hill
通讯作者: P. Reiff;R. Spiro;T. Hill
DOI: 10.1029/ja085ia05p02335
发表时间: 1980-05
影响因子: --
作者:
F. Rich;W. J. Burke;M. Kelley;M. Smiddy
通讯作者: F. Rich;W. J. Burke;M. Kelley;M. Smiddy
DOI: 10.1029/ja088ia11p09125
发表时间: 1983-11
影响因子: --
作者:
M. A. Doyle;W. J. Burke
通讯作者: M. A. Doyle;W. J. Burke
DOI: 10.1016/j.asr.2013.06.019
发表时间: 2013-09
影响因子: 2.6
作者:
D. Mori;A. Koustov
通讯作者: D. Mori;A. Koustov
DOI: 10.1029/2011ja016924
发表时间: 2011-12
影响因子: --
作者:
F. Wilder;C. Clauer;J. Baker;E. Cousins;M. Hairston
通讯作者: F. Wilder;C. Clauer;J. Baker;E. Cousins;M. Hairston