Prediction of magnetization dynamics in a reduced dimensional feature space setting utilizing a low-rank kernel method

We establish a machine learning model for the prediction of the magnetization dynamics as function of the external field described by the Landau-Lifschitz-Gilbert equation, the partial differential equation of motion in micromagnetism. The model allows for fast and accurate determination of the response to an external field which is illustrated by a thin-film standard problem. The data-driven method internally reduces the dimensionality of the problem by means of nonlinear model reduction for unsupervised learning. This not only makes accurate prediction of the time steps possible, but also decisively reduces complexity in the learning process where magnetization states from simulated micromagnetic dynamics associated with different external fields are used as input data. We use a truncated representation of kernel principal components to describe the states between time predictions. The method is capable of handling large training sample sets owing to a low-rank approximation of the kernel matrix and an associated low-rank extension of kernel principal component analysis and kernel ridge regression. The approach entirely shifts computations into a reduced dimensional setting breaking down the problem dimension from the thousands to the tens.

[1]  Bernhard Schölkopf,et al.  Learning to Find Pre-Images , 2003, NIPS.

[2]  M. d’Aquino,et al.  Geometrical integration of Landau-Lifshitz-Gilbert equation based on the mid-point rule , 2005 .

[3]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[4]  M. Gusenbauer,et al.  Learning magnetization dynamics , 2019, Journal of Magnetism and Magnetic Materials.

[5]  Spectral micromagnetic analysis of switching processes , 2009 .

[6]  Saburou Saitoh,et al.  Theory of Reproducing Kernels and Its Applications , 1988 .

[7]  Helmut Kronmüller General Micromagnetic Theory , 2007 .

[8]  Bernhard Schölkopf,et al.  Kernel Principal Component Analysis , 1997, ICANN.

[9]  Nicole Propst,et al.  Introduction To The Theory Of Ferromagnetism , 2016 .

[10]  Werner Scholz,et al.  Time resolved micromagnetics using a preconditioned time integration method , 2002 .

[11]  Vladimir Vovk,et al.  Kernel Ridge Regression , 2013, Empirical Inference.

[12]  Thomas Schrefl,et al.  Numerical Methods in Micromagnetics (Finite Element Method) , 2007 .

[13]  Sebastian Luber,et al.  Topologically protected vortex structures for low-noise magnetic sensors with high linear range , 2018, Nature Electronics.

[14]  Thomas Schrefl,et al.  The extrapolated explicit midpoint scheme for variable order and step size controlled integration of the Landau-Lifschitz-Gilbert equation , 2017, J. Comput. Phys..

[15]  Michael J. Donahue,et al.  Numerical Micromagnetics: Finite Difference Methods , 2007 .

[16]  Gökhan BakIr,et al.  A General Regression Framework for Learning String-to-String Mappings , 2007 .

[17]  S. Parkin,et al.  Handbook of magnetism and advanced magnetic materials , 2007 .

[18]  L. Exl A magnetostatic energy formula arising from the L2-orthogonal decomposition of the stray field , 2016, Journal of Mathematical Analysis and Applications.

[19]  Jason Weston,et al.  A General Regression Framework for Learning String-to-String Mappings , 2006 .

[20]  Markus Gusenbauer,et al.  Micromagnetics of rare-earth efficient permanent magnets , 2018, 1903.11922.

[21]  M J Donahue,et al.  OOMMF User's Guide, Version 1.0 , 1999 .

[22]  M. d’Aquino,et al.  Large scale finite-element simulation of micromagnetic thermal noise , 2018, Journal of Magnetism and Magnetic Materials.

[23]  Dieter Suess,et al.  Learning time-stepping by nonlinear dimensionality reduction to predict magnetization dynamics , 2020, Commun. Nonlinear Sci. Numer. Simul..

[24]  Bernhard Schölkopf,et al.  Kernel Dependency Estimation , 2002, NIPS.

[25]  Lukas Exl,et al.  Numerical methods for the stray-field calculation: A comparison of recently developed algorithms , 2012, 1204.4302.

[26]  Michael Rabadi,et al.  Kernel Methods for Machine Learning , 2015 .

[27]  Shai Ben-David,et al.  Understanding Machine Learning: From Theory to Algorithms , 2014 .