Physics-Informed Neural Networks for Modeling the Martian Induced Magnetosphere

TL;DR

This paper introduces a novel data-driven approach using Physics-Informed Neural Networks to model Mars's induced magnetosphere, providing accurate magnetic field reconstructions driven by solar wind conditions, and revealing key dependencies and asymmetries.

Contribution

It is the first application of PINNs to model the Martian magnetosphere, integrating observational data with physical laws for efficient and accurate magnetic field predictions.

Findings

PINNs accurately reconstruct 3D magnetic fields around Mars.

The model reveals hemispheric asymmetries in magnetic field strength.

Key solar wind parameters influence magnetic field configuration.

Abstract

Understanding the magnetic field environment around Mars and its response to upstream solar wind conditions provide key insights into the processes driving atmospheric ion escape. To date, global models of Martian induced magnetosphere have been exclusively physics-based, relying on computationally intensive simulations. For the first time, we develop a data-driven model of the Martian induced magnetospheric magnetic field using Physics-Informed Neural Network (PINN) combined with MAVEN observations and physical laws. Trained under varying solar wind conditions, including B_IMF, P_SW, and {\theta}_cone, the data-driven model accurately reconstructs the three-dimensional magnetic field configuration and its variability in response to upstream solar wind drivers. Based on the PINN results, we identify key dependencies of magnetic field configuration on solar wind parameters, including the hemispheric asymmetries of the draped field line strength in the Mars-Solar-Electric coordinates. These findings demonstrate the capability of PINNs to reconstruct complex magnetic field structures in the Martian induced magnetosphere, thereby offering a promising tool for advancing studies of solar wind-Mars interactions.