Abstract

In this study, the relationship between moderate and extremely high levels of geomagnetic activity, represented by the Kp index (2- to 5 + and 6- to 9), and solar wind conditions during southward IMF intervals was revealed utilizing a newly developed machine learning technique. Potential learning (PL) is a neural network algorithm that emphasizes input parameters with the highest variance during training and identifies the most significant input parameters influencing the outputs based on a computed metric called “potentiality”. We focus on discussing the dependence of solar wind plasma density on moderate-geomagnetic conditions. It has poorly been understood from what stage of geomagnetic activity the solar wind density begins to control the Kp level. Previously, PL extracted the solar wind velocity as the most predominant parameter at extremely low (0 to 1 +)- and high-Kp ranges under southward interplanetary magnetic field (IMF) conditions. Also in this study, the IMF three components, solar wind flow speed, and plasma density obtained from the OMNI solar wind database (1998–2019), corresponding from solar cycle 23 to beginning of cycle 25, were used as the input parameters. Again, PL selected the solar wind velocity as the most significant parameter for the moderate and extremely high Kp levels. The potentiality of solar wind density for these Kp ranges was, however, 3.5 times higher than that in the previous study, suggesting that its impact on geomagnetic activity cannot be ignored. We statistically investigated the relation between solar wind speed and plasma density used as the PL input data under all Kp levels. At higher than the moderate Kp level, geomagnetic conditions become high even under slow solar wind velocity, if the plasma density is large, suggesting that not only solar wind velocity but also plasma density might significantly contribute to geomagnetic activity. These PL and incidental statistical investigations show that the solar wind density begins to regulate Kp higher than moderate geomagnetic activity level under southward IMF conditions. They also would greatly help not only understand general relationship between solar wind conditions and geomagnetic activity but also forecast geomagnetic activity under various IMF conditions.