Physics-driven Machine Learning for the Prediction of Coronal Mass Ejections’ Travel Times
Physics-driven Machine Learning for the Prediction of Coronal Mass Ejections’ Travel Times
复制标题
用于预测日冕物质抛射传播时间的物理驱动机器学习
DOI：
10.3847/1538-4357/ace62d
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
M. Piana
中科院分区：
文献类型：
--
作者：
S. Guastavino;Valentina Candiani;A. Bemporad;Francesco Marchetti;F. Benvenuto;A. Massone;S. Mancuso;R. Susino;D. Telloni;S. Fineschi;M. Piana
日冕物质抛射（cme）是指太阳日冕向日球层剧烈地喷射等离子体和磁场。日冕物质抛射在科学上是相关的，因为它们涉及表征活跃太阳的物理机制。然而，最近，日冕物质抛射对空间天气的影响引起了人们的注意，因为它们与地磁风暴有关，并可能诱发太阳高能粒子流的产生。在这个空间天气框架中，本文介绍了一种物理驱动的人工智能（AI）方法来预测cme的传播时间，其中利用确定性的基于阻力的模型来改进两个神经网络级联的训练阶段，这些神经网络由遥感和现场数据提供。本研究表明，在人工智能架构中使用物理信息显著提高了旅行时间预测的准确性和鲁棒性。
Coronal Mass Ejections (CMEs) correspond to dramatic expulsions of plasma and magnetic field from the solar corona into the heliosphere. CMEs are scientifically relevant because they are involved in the physical mechanisms characterizing the active Sun. However, more recently, CMEs have attracted attention for their impact on space weather, as they are correlated to geomagnetic storms and may induce the generation of solar energetic particle streams. In this space weather framework, the present paper introduces a physics-driven artificial intelligence (AI) approach to the prediction of CMEs’ travel time, in which the deterministic drag-based model is exploited to improve the training phase of a cascade of two neural networks fed with both remote sensing and in situ data. This study shows that the use of physical information in the AI architecture significantly improves both the accuracy and the robustness of the travel time prediction.
DOI：
10.3847/2041-8213/abcb03
发表时间：
2020-12
期刊：
The Astrophysical Journal Letters
影响因子：
--
作者：
D. Telloni;Lingling Zhao;G. Zank;Haoming Liang;M. Nakanotani;L. Adhikari;F. Carbone;R. D’Amicis
通讯作者：
D. Telloni;Lingling Zhao;G. Zank;Haoming Liang;M. Nakanotani;L. Adhikari;F. Carbone;R. D’Amicis