Saved in:
Bibliographic Details
Main Authors: Mansouri, Reza, Kempton, Dustin, Riley, Pete, Angryk, Rafal
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.20830
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914407695515648
author Mansouri, Reza
Kempton, Dustin
Riley, Pete
Angryk, Rafal
author_facet Mansouri, Reza
Kempton, Dustin
Riley, Pete
Angryk, Rafal
contents The solar wind, a continuous outflow of charged particles from the Sun's corona, shapes the heliosphere and impacts space systems near Earth. Accurate prediction of features such as high-speed streams and coronal mass ejections is critical for space weather forecasting, but traditional three-dimensional magnetohydrodynamic (MHD) models are computationally expensive, limiting rapid exploration of boundary condition uncertainties. We introduce the first autoregressive machine learning surrogate for steady-state solar wind radial velocity using the Spherical Fourier Neural Operator (SFNO). By predicting a limited radial range and iteratively propagating the solution outward, the model improves accuracy in distant regions compared to a single-step approach. Compared with the numerical HUX surrogate, SFNO demonstrates superior or comparable performance while providing a flexible, trainable, and data-driven alternative, establishing a novel methodology for high-fidelity solar wind modeling. The source code and additional visual results are available at https://github.com/rezmansouri/solarwind-sfno-velocity-autoregressive.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20830
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Autoregressive Surrogate Modeling of the Solar Wind with Spherical Fourier Neural Operator
Mansouri, Reza
Kempton, Dustin
Riley, Pete
Angryk, Rafal
Machine Learning
The solar wind, a continuous outflow of charged particles from the Sun's corona, shapes the heliosphere and impacts space systems near Earth. Accurate prediction of features such as high-speed streams and coronal mass ejections is critical for space weather forecasting, but traditional three-dimensional magnetohydrodynamic (MHD) models are computationally expensive, limiting rapid exploration of boundary condition uncertainties. We introduce the first autoregressive machine learning surrogate for steady-state solar wind radial velocity using the Spherical Fourier Neural Operator (SFNO). By predicting a limited radial range and iteratively propagating the solution outward, the model improves accuracy in distant regions compared to a single-step approach. Compared with the numerical HUX surrogate, SFNO demonstrates superior or comparable performance while providing a flexible, trainable, and data-driven alternative, establishing a novel methodology for high-fidelity solar wind modeling. The source code and additional visual results are available at https://github.com/rezmansouri/solarwind-sfno-velocity-autoregressive.
title Autoregressive Surrogate Modeling of the Solar Wind with Spherical Fourier Neural Operator
topic Machine Learning
url https://arxiv.org/abs/2511.20830