Identification of Flux Rope Orientation via Neural Networks

TL;DR

This paper demonstrates that convolutional neural networks can predict the magnetic flux rope orientation in solar wind data, improving real-time geomagnetic disturbance forecasting by automating a traditionally manual process.

Contribution

It introduces a CNN-based method trained on simulated flux ropes to accurately determine flux rope orientation from in situ observations, including partial data scenarios.

Findings

CNNs achieve high accuracy with full flux rope data

Partial flux rope observations still enable reliable orientation predictions

Evaluation on Wind data validates the model's practical applicability

Abstract

Geomagnetic disturbance forecasting is based on the identification of solar wind structures and accurate determination of their magnetic field orientation. For nowcasting activities, this is currently a tedious and manual process. Focusing on the main driver of geomagnetic disturbances, the twisted internal magnetic field of interplanetary coronal mass ejections (ICMEs), we explore a convolutional neural network's (CNN) ability to predict the embedded magnetic flux rope's orientation once it has been identified from in situ solar wind observations. Our work uses CNNs trained with magnetic field vectors from analytical flux rope data. The simulated flux ropes span many possible spacecraft trajectories and flux rope orientations. We train CNNs first with full duration flux ropes and then again with partial duration flux ropes. The former provides us with a baseline of how well CNNs can predict flux rope orientation while the latter provides insights into real-time forecasting by exploring how accuracy is affected by percentage of flux rope observed. The process of casting the physics problem as a machine learning problem is discussed as well as the impacts of different factors on prediction accuracy such as flux rope fluctuations and different neural network topologies. Finally, results from evaluating the trained network against observed ICMEs from Wind during 1995-2015 are presented.