Neural Operator based Multi-Field Reconstruction of Inner Solar Boundary State
2026-08-24 • Machine Learning
Machine LearningComputer Vision and Pattern Recognition
AI summaryⓘ
The authors address how to better predict the solar wind—a flow of charged particles from the sun—by improving the input information used in models. They focus on estimating missing but important magnetic and velocity details at a specific distance from the sun using a special kind of machine learning called a Local Neural Operator. This method learns complex, multi-scale relationships in solar data more effectively than traditional approaches. Their work aims to provide more complete boundary conditions that future solar wind and space weather models can use.
Solar windMagnetohydrodynamicsInner-boundary conditionsRadial velocityRadial magnetic fieldNeural operatorLocal Neural OperatorMulti-scale modelingFunction space mappingHeliospheric modeling
Authors
Vignesh Kumar Pandian Sathia, Reza Mansouri, Dustin J. Kempton, Pete Riley, Rafal A. Angryk
Abstract
The Solar wind is a continuous flow of charged particles emanating from the solar surface and governed by complex, interacting magnetohydrodynamic processes. Accurate specification of inner-boundary conditions is essential for heliospheric modeling and solar-wind prediction. In many practical applications, only a subset of interacting multi-field variables is directly available, but for a comprehensive view of solar wind prediction and downstream magnetohydrodynamic simulations, a more complete boundary state is required. In this work, we study the problem of learning the multi-field multi-scale solar magnetohydrodynamic state at 30 solar radii ($R_\odot$) using operator learning. Specifically, given the radial velocity and radial magnetic field, we aim to reconstruct the non-radial velocity and magnetic field components, radial and non-radial current density, thermodynamic density, and pressure components. This mapping is highly nonlinear, spatially coupled, and multi-scale, making it a challenging task for data-driven scientific machine learning. To address this problem, we employ a Local Neural Operator (LocalNO) that learns mappings between input and output function spaces while retaining locality and resolution-awareness. Unlike conventional regression models and autoencoder models, neural operators are better suited for learning structured field-to-field transformations arising from physical systems. The resulting predictions along with inputs are intended to serve as boundary condition variables for future inner-heliospheric modeling pipelines.