Which Upstream Solar Wind Conditions Matter Most in Predicting Bz Within Coronal Mass Ejections

Accurately predicting the z‐component of the interplanetary magnetic field, particularly during the passage of an interplanetary coronal mass ejection (ICME), is a crucial objective for space weather predictions. Currently, only a handful of techniques have been proposed and they remain limited in scope and accuracy. Recently, a robust machine learning technique was developed for predicting the minimum value of Bz within ICMEs based on a set of 42 “features,” that is, variables calculated from measured quantities upstream of the ICME and within its sheath region. In this study, we investigate these so‐called explanatory variables in more detail, focusing on those that were (a) statistically significant and (b) most important. We find that number density and magnetic field strength accounted for a large proportion of the variability. These features capture the degree to which the ICME compresses the ambient solar wind ahead. Intuitively, this makes sense: Energy made available to coronal mass ejections (CMEs) as they erupt is partitioned into magnetic and kinetic energy. Thus, more powerful CMEs are launched with larger flux‐rope fields (larger Bz), at greater speeds, resulting in more sheath compression (increased number density and total field strength). Plain Language Summary As our society becomes more technologically reliant, the need to accurately forecast the severity of geomagnetic storms becomes increasingly important. Storms driven by fast coronal mass ejections (CMEs) represent the biggest threat, being responsible for all of the major geomagnetic events in recorded history, in part, because they contain the largest magnetic fields within them. Fast CMEs plowing through the solar wind produce a so‐called “sheath” region ahead of them. In this study, we relate the properties of the sheath region to the size of the CME's magnetic field, demonstrating that estimates of compression provide the most robust predictions of the ensuing magnetic field. This relationship is a promising forecasting approach that could provide more than 1 day's advance warning before the arrival of the peak magnetic fields within the CME. Key Points Machine learning algorithms driven by features within the upstream sheath region can accurately predict minimum values of Bz within the ejecta The most important and statistically significant features are sheath number density and total field strength These features capture compression upstream of the interplanetary coronal mass