Prediction of Proton Pressure in the Outer Part of the Inner Magnetosphere Using Machine Learning.

The information on plasma pressure in the outer part of the inner magnetosphere is important for simulations of the inner magnetosphere and a better understanding of its dynamics. Based on 17‐year observations from both Cluster Ion Spectrometry and Research with Adaptive Particle Imaging Detector instruments onboard the Cluster mission, we used machine‐learning‐based models to predict proton plasma pressure at energies from ∼40 eV to 4 MeV in the outer part of the inner magnetosphere (L∗ ${L}^{\ast }$ = 5–9). Proton pressure distributions are assumed to be isotropic. The location in the magnetosphere, the property of stably trapped particles, and parameters of solar, solar wind, and geomagnetic activity from the OMNI database are used as predictors. We trained several different machine‐learning‐based models and compared their performances with observations. The results demonstrate that the Extra‐Trees Regressor has the best predicting performance. The Spearman correlation between the observations and predictions by the model is about 70%. The most important parameter for predicting proton pressure in our model is the L∗ ${L}^{\ast }$ value, which relates to the property of stably trapped particles. The most important predictor of solar and geomagnetic activity is F10.7 index. Based on the observations and predictions by our model, we find that no matter under quiet or disturbed geomagnetic conditions, both the dusk‐dawn asymmetry at the dayside with higher pressure at the duskside and the day‐night asymmetry with higher pressure at the nightside occur. Our results have direct practical applications, for instance, inputs for simulations of the inner magnetosphere or the reconstruction of the 3‐D magnetospheric electric current system based on the magnetostatic equilibrium. Plain Language Summary: The distribution of the plasma pressure in the magnetosphere is a key parameter for the assessment of the magnetostatic equilibrium, the dynamics of geomagnetic storms, and the magnetospheric electric current system. In addition, the outer part of the inner magnetosphere is often used as the boundary in the inner magnetosphere simulations, where the initial composition is specified. Thus, the distribution of the plasma pressure at this boundary is essential for the simulations of the inner magnetosphere and understanding of the underlying magnetospheric dynamic processes. Although, there are many previous studies on the distribution of plasma pressure, building a model to predict the 3‐D distribution of proton pressure remains challenging. Based on 17 years of data from the Cluster spacecraft mission, a machine‐learning‐based model for predicting proton pressure at energies from ∼40 eV to 4 MeV in the outer part of the inner magnetosphere is built. We set up the 3‐D model for the prediction of the proton pressure depending on the location, the property of stably trapped particles, solar wind, and geomagnetic activity indices. The model gives reliable predictions and can be used for the interpretation of the dynamics of the inner magnetosphere under different geomagnetic conditions. Key Points: A machine learning model is created to predict the 3‐D distribution of proton pressure at L∗ ${L}^{\ast }$ = 5–9 for energies ∼40 eV–4 MeVOur model based on Extra‐Trees Regressor reproduces well the global distributions as well as the pressure along a spacecraft trajectoryThe results of our model are helpful for the interpretation of proton pressure in the outer part of the magnetosphere [ABSTRACT FROM AUTHOR]