A Deep Learning‐Based Approach to Forecast the Onset of Magnetic Substorms

A Deep Learning‐Based Approach to Forecast the Onset of Magnetic Substorms
复制标题

基于深度学习的方法来预测磁亚暴的爆发

DOI:
10.1029/2019sw002251
复制
发表时间:
2019
期刊:
影响因子:
3.7
通讯作者:
House, Leanna L.
House, Leanna L.
中科院分区:
地球科学1区
文献类型:
--
作者:
Maimaiti, M.;Kunduri, B.;Ruohoniemi, J. M.;Baker, J. B. H.;House, Leanna L.

文献摘要

参考文献

被引文献

相似文献

在过去的60年里,人们对极光亚暴进行了广泛的研究。然而,我们对其驱动机制的理解仍然有限,因此我们准确预测其发病的能力也是有限的。在这项研究中,我们提出了第一个基于深度学习的方法来预测磁亚暴的发生,定义为地面磁力计测量中极光电喷流的特征。具体来说,我们使用太阳风速度(Vx)、质子数密度和行星际磁场(IMF)分量的时程作为输入,来预测未来1小时内爆发的发生概率。该模型已经在SuperMAG磁暴发作列表的数据集上进行了训练和测试,可以在75%的时间内正确识别亚暴。相比之下,较早的预测算法可以正确识别同一数据集中约21%的亚暴。我们的模型基于太阳风和IMF在实际开始时间之前的输入来预测亚暴的能力,以及在imfb中观察到的开始时间之前的趋势,共同表明大多数亚暴可能不是由IMF向北转向的外部触发的。此外,我们发现imfbzzand vxx对模型性能的影响最为显著。最后,主成分分析显示,在亚暴和非亚暴间隔之前,太阳风和IMF参数都有显著程度的重叠,这表明仅靠太阳风和IMF可能不足以预测所有亚暴,磁尾的预处理可能是一个重要因素。
The auroral substorm has been extensively studied over the last six decades. However, our understanding of its driving mechanisms is still limited and so is our ability to accurately forecast its onset. In this study, we present the first deep learning‐based approach to predict the onset of a magnetic substorm, defined as the signature of the auroral electrojets in ground magnetometer measurements. Specifically, we use a time history of solar wind speed (Vx), proton number density, and interplanetary magnetic field (IMF) components as inputs to forecast the occurrence probability of an onset over the next 1 hr. The model has been trained and tested on a data set derived from the SuperMAG list of magnetic substorm onsets and can correctly identify substorms ∼75% of the time. In contrast, an earlier prediction algorithm correctly identifies ∼21% of the substorms in the same data set. Our model's ability to forecast substorm onsets based on solar wind and IMF inputs prior to the actual onset time, and the trend observed in IMFBzprior to onset together suggest that a majority of the substorms may not be externally triggered by northward turnings of IMF. Furthermore, we find that IMFBzandVxhave the most significant influence on model performance. Finally, principal component analysis shows a significant degree of overlap in the solar wind and IMF parameters prior to both substorm and nonsubstorm intervals, suggesting that solar wind and IMF alone may not be sufficient to forecast all substorms, and preconditioning of the magnetotail may be an important factor.
DOI: 10.1029/2004ja010488
发表时间: 2004-12
影响因子: --
作者:
A. Kullen;T. Karlsson
通讯作者: A. Kullen;T. Karlsson
DOI: --
发表时间: 2009
期刊:
影响因子: --
作者:
A. Kullen;S. Ohtani;T. Karlsson
通讯作者: T. Karlsson
监督学习-使用逻辑回归进行分类
DOI: --
发表时间: 2019
期刊: Machine-mediated learning
影响因子: --
作者:
A. Kullen;S. Ohtani;T. Karlsson
通讯作者: T. Karlsson
使用监督学习算法根据观测数据预测极光亚暴
DOI: --
发表时间: 2015
期刊: IEEE International Conference on e-Science
影响因子: --
作者:
Takanori Tanaka;Daisuke Kitao;Yuka Sato;Yoshimasa Tanaka;D. Ikeda
通讯作者: D. Ikeda
地磁活动的神经网络预测
DOI: --
发表时间: 1993
期刊:
影响因子: --
作者:
J. Hernández;T. Tajima;W. Horton
通讯作者: W. Horton