Identifying Flux Rope Signatures Using a Deep Neural Network
- PDF / 3,350,978 Bytes
- 29 Pages / 439.37 x 666.142 pts Page_size
- 47 Downloads / 215 Views
Identifying Flux Rope Signatures Using a Deep Neural Network Luiz F. G. dos Santos1,2 · Ayris Narock1,3 · Teresa Nieves-Chinchilla1 · Marlon Nuñez4 · Michael Kirk1,5
Received: 9 April 2020 / Accepted: 28 August 2020 © Springer Nature B.V. 2020
Abstract Among the current challenges in space weather, one of the main ones is to forecast the internal magnetic configuration within interplanetary coronal mass ejections (ICMEs). The classification of such an arrangement is essential to predict geomagnetic disturbances. When a monotonic and coherent magnetic configuration is observed, it is associated with the result of a spacecraft crossing a large flux rope with the topology of helical magnetic field lines. This article applies machine learning and a current physical flux rope analytical model to identify and further understand the internal structure of ICMEs. We trained an image recognition artificial neural network with analytical flux rope data, generated from the range of many possible trajectories within a cylindrical (circular and elliptical crosssection) model. The trained network was then evaluated against the observed ICMEs from Wind during 1995–2015. The methodology developed in this article can classify 84% of simple real cases correctly and has a 76% success rate when extended to a broader set with 5% noise applied, although it does exhibit a bias in favor of positive flux rope classification. As a first step towards a generalizable classification and parameterization tool, these results are promising. With further tuning and refinement, our model presents a strong potential to evolve into a robust tool for identifying flux rope configurations from in situ data. This article belongs to the Topical Collection: Towards Future Research on Space Weather Drivers Guest Editors: Hebe Cremades and Teresa Nieves-Chinchilla
B L.F.G. dos Santos
[email protected] A. Narock [email protected]
1
Heliophysics Science Division, NASA, Goddard Space Flight Center, Greenbelt, MD 20771, USA
2
The Catholic University of America, 620 Michigan Avenue NE, Washington, DC 20064, USA
3
ADNET Systems Inc., 7515 Mission Drive, Lanham, MD 20706, USA
4
Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, Campus de Teatinos, 29071 Málaga, Spain
5
ASTRA, LLC., 282 Century Place Suite 1000, Louisville, CO 80027, USA
131
Page 2 of 29
L.F.G. dos Santos et al.
Keywords Coronal mass ejections · Interplanetary · Magnetic fields · Models · Machine learning · Deep learning · Convolutional neural network · Handwriting recognition · Magnetic field fluctuations
1. Introduction The main drivers of geomagnetic activity are interplanetary coronal mass ejections (ICMEs). Besides transporting large quantities of mass and magnetic flux away from the Sun, their internal magnetic field structure is often coupled to the upper magnetosphere, triggering magnetic reconnection processes that allow solar magnetic energy to be injected into the entire magnetospheric system. Thus, a reliable classi
Data Loading...
