Machine Learning Solar Wind Driving Magnetospheric Convection in Tail Lobes

TL;DR

This study employs machine learning to analyze how upstream solar wind conditions influence magnetospheric convection in the tail lobes, revealing the significant roles of IMF and activity levels in driving plasma dynamics.

Contribution

The paper introduces a machine learning approach to quantitatively identify upstream drivers of magnetotail lobe convection, outperforming traditional linear regression models.

Findings

Machine learning models achieve correlation >0.75 with observed convection velocities.

IMF and magnetospheric activity significantly influence tail lobe plasma convection.

Machine learning provides better predictive insights than linear regression.

Abstract

To quantitatively study the driving mechanisms of magnetospheric convection in the magnetotail lobes on a global scale, we utilize data from the ARTEMIS spacecraft in the deep tail and the Cluster spacecraft in the near tail. Previous work demonstrated that, in the lobes near the Moon, we can estimate the convection by utilizing ARTEMIS measurements of lunar ions velocity. In this paper, we analyze these datasets with machine learning models to determine what upstream factors drive the lobe convection in different magnetotail regions and thereby understand the mechanisms that control the dynamics of the tail lobes. Our results show that the correlations between the predicted and test convection velocities for the machine learning models (>0.75) are much better than those of the multiple linear regression model (~ 0.23 - 0.43). The systematic analysis reveals that the IMF and magnetospheric activity play an important role in influencing plasma convection in the global magnetotail lobes.