Skip to main navigation Skip to search Skip to main content

Learning time-stepping by nonlinear dimensionality reduction to predict magnetization dynamics

Publications: Contribution to journalArticlePeer Reviewed

Abstract

We establish a time-stepping learning algorithm and apply it to predict the solution of the partial differential equation of motion in micromagnetism as a dynamical system depending on the external field as parameter. The data-driven approach is based on nonlinear model order reduction by use of kernel methods for unsupervised learning, yielding a predictor for the magnetization dynamics without any need for field evaluations after a data generation and training phase as precomputation. Magnetization states from simulated micromagnetic dynamics associated with different external fields are used as training data to learn a low-dimensional representation in so-called feature space and a map that predicts the time-evolution in reduced space. Remarkably, only two degrees of freedom in feature space were enough to describe the nonlinear dynamics of a thin-film element. The approach has no restrictions on the spatial discretization and might be useful for fast determination of the response to an external field.
Original languageEnglish
Article number105205
Number of pages8
JournalCommunications in Nonlinear Science and Numerical Simulation
Volume84
Early online date22 Jan 2020
DOIs
Publication statusPublished - May 2020

Austrian Fields of Science 2012

  • 101014 Numerical mathematics
  • 102019 Machine learning
  • 103018 Materials physics

Keywords

  • physics.comp-ph
  • cond-mat.mtrl-sci
  • 37M05, 62P35, 65Z05
  • INTEGRATION
  • Kernel principal component analysis
  • Machine learning
  • Micromagnetics
  • Nonlinear model order reduction
  • Kernelization

Cite this