Automatic detection of large-scale flux ropes and their geoeffectiveness with a machine learning approach

Abstract

Detecting large-scale flux ropes (FRs) embedded in interplanetary coronal mass ejections (ICMEs) and assessing their geoeffectiveness are essential since they can drive severe space weather. At 1 au, these FRs have an average duration of 1 day. Their most common magnetic features are large, smoothly rotating magnetic fields. Their manual detection has become a relatively common practice over decades, although visual detection can be time-consuming and subject to observer bias. Our study proposes a pipeline that utilizes two supervised binary-classification machine learning (ML) models trained with solar wind magnetic properties to automatically detect large-scale FRs and additionally determine their geoeffectiveness. The first model is used to generate a list of auto-detected FRs. Using the properties of southward magnetic field the second model determines the geoeffectiveness of FRs. Our method identifies 88.6\% and 80\% large-scale ICMEs (duration $\ge 1$ day) observed at 1 au by Wind and Sun Earth Connection Coronal and Heliospheric Investigation (STEREO) mission, respectively. While testing with a continuous solar wind data obtained from Wind, our pipeline detected 56 of the 64 large-scale ICMEs during 2008 - 2014 period (recall= 0.875) but many false positives (precision= 0.56) as we do not take into account any additional solar wind properties than the magnetic properties. We found an accuracy of 0.88 when estimating the geoeffectiveness of the auto-detected FRs using our method. Thus, in space weather now-casting and forecasting at L1 or any planetary missions, our pipeline can be utilized to offer a first-order detection of large-scale FRs and geoeffectiveness.

19 pages, 6 figures

References in corpus (12)

• The Solar Orbiter mission -- Science overview
• The Evolution and Role of Solar Wind Turbulence in the Inner Heliosphere
• Multi-Hour Ahead Dst Index Prediction Using Multi-Fidelity Boosted Neural Networks
• Flux erosion of magnetic clouds by reconnection with the Sun's open flux
• A Catalog of Interplanetary Coronal Mass Ejections Observed by Juno between 1 and 5.4 AU
• Automatic detection of Interplanetary Coronal Mass Ejections from in-situ data: a deep learning approach
• A magnetic cloud prediction model for forecasting space weather relevant properties of Earth-directed coronal mass ejections
• Turbulence Properties of Interplanetary Coronal Mass Ejections in the Inner Heliosphere: Dependence on Proton Beta and Flux Rope Structure
• Probabilistic prediction of Dst storms one-day-ahead using Full-Disk SoHO Images
• Automatic Detection of Interplanetary Coronal Mass Ejections in Solar Wind In Situ Data
• Writhed Analytical Magnetic Flux Rope Model
• Distorted-Toroidal Flux Rope model for Heliospheric Flux Ropes

Cited by in corpus (1)

• Magnetic interaction analysis of multiple interplanetary coronal mass ejections leading to a historic geomagnetic storm in May 2024