摘要：Global magnetohydrodynamic (MHD) modeling is a powerful tool in space weather research and predictions. There are several advanced and still developing global MHD (GMHD) models that are publicly available via Community Coordinated Modeling Center's (CCMC) Run on Request system, which allows the users to simulate the magnetospheric response to different solar wind conditions including extraordinary events, like geomagnetic storms. Systematic validation of GMHD models against observations still continues to be a challenge, as well as comparative benchmarking of different models against each other. In this paper we describe and test a new approach in which (i) a set of critical large-scale system parameters is explored/tested, which are produced by (ii) specially designed set of computer runs to simulate realistic statistical distributions of critical solar wind parameters and are compared to (iii) observation-based empirical relationships for these parameters. Being tested in approximately similar conditions (similar inputs, comparable grid resolution, etc.), the four models publicly available at the CCMC predict rather well the absolute values and variations of those key parameters (magnetospheric size, magnetic field, and pressure) which are directly related to the large-scale magnetospheric equilibrium in the outer magnetosphere, for which the MHD is supposed to be a valid approach. At the same time, the models have systematic differences in other parameters, being especially different in predicting the global convection rate, total field-aligned current, and magnetic flux loading into the magnetotail after the north-south interplanetary magnetic field turning. According to validation results, none of the models emerges as an absolute leader. The new approach suggested for the evaluation of the models performance against reality may be used by model users while planning their investigations, as well as by model developers and those interesting to quantitatively evaluate progress in magnetospheric modeling.
