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

TL;DR

This paper introduces a machine learning pipeline for automatic detection of large-scale flux ropes in interplanetary space and assesses their potential to cause space weather effects, improving speed and reducing bias over manual methods.

Contribution

The study develops a novel ML-based pipeline that automatically detects flux ropes and evaluates their geoeffectiveness using only magnetic properties, achieving high detection accuracy.

Findings

Detected 88.6% and 80% of large-scale ICMEs at 1 au by Wind and STEREO.

Achieved 87.5% recall in identifying ICMEs during 2008-2014.

Estimated geoeffectiveness with 88% accuracy.

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.