Identifying Flux Rope Signatures Using a Deep Neural Network

• Published in: Solar physics Vol. 295; no. 10
• Main Authors: dos Santos, Luiz F. G., Narock, Ayris, Nieves-Chinchilla, Teresa, Nuñez, Marlon, Kirk, Michael
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.10.2020; Springer Nature B.V
• Subjects: Artificial neural networks; Astrophysics and Astroparticles; Atmospheric Sciences; Classification; Configurations; Coronal mass ejection; Fluctuations; Geomagnetic disturbances; Geomagnetism; Machine learning; Magnetic fields; Magnetic flux; Mathematical models; Neural networks; Object recognition; Parameterization; Physics; Physics and Astronomy; Solar physics; Space Exploration and Astronautics; Space Sciences (including Extraterrestrial Physics; Space weather; Spacecraft; Topology; Towards Future Research on Space Weather Drivers; Voyager 1 spacecraft; Deep learning; Handwriting recognition; Magnetic field fluctuations; Convolutional neural network; Machine learning; Coronal mass ejections; Models; Interplanetary; Magnetic fields
• ISSN: 0038-0938; 1573-093X
• DOI: 10.1007/s11207-020-01697-x

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 cross-section) 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.