Understanding the Magnetic Microstructure through Experiments and Machine Learning Algorithms

Funding Information: The ion-beam experiments were performed at the LEIBF beamline of Inter University Accelerator Center (IUAC), New Delhi, India. U.G. has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement no. 861145-BeMAGIC. U.G. is grateful to S. Picozzi (CNR-SPIN) and K. Govind for inspiration and insightful discussions. J.R.M. acknowledges the funding support from DST Nanomission (project no. DST/NM/TUE/QM-4/2019-IIT-H), Govt. of India. A.T. and S.P.P. acknowledge the funding from IEEE Magnetics Society. Prof. Dr. Stefan Eisebit and Dr. Christian Günther are thanked for providing the magnetic multilayer samples. Prof. Tamaki Shibayama is acknowledged for helping with the TEM measurements. Publisher Copyright: © 2022 American Chemical Society. All rights reserved.Advanced machine learning techniques have unfurled their applications in various interdisciplinary areas of research and development. This paper highlights the use of image regression algorithms based on advanced neural networks to understand the magnetic properties directly from the magnetic microstructure. In this study, Co/Pd multilayers have been chosen as a reference material system that displays maze-like magnetic domains in pristine conditions. Irradiation of Ar+ ions with two different energies (50 and 100 keV) at various fluences was used as an external perturbation to investigate the modification of magnetic and structural properties from a state of perpendicular magnetic anisotropy to the vicinity of the spin reorientation transition. Magnetic force microscopy revealed domain fragmentation with a smaller periodicity and weaker magnetic contrast up to the fluence of 1014 ions/cm2. Further increases in the ion fluence result in the formation of feather-like domains with a variation in local magnetization distribution. The experimental results were complemented with micromagnetic simulations, where the variations of effective magnetic anisotropy and exchange constant result in qualitatively similar changes in magnetic domains, as observed experimentally. Importantly, a set of 960 simulated domain images was generated to train, validate, and test the convolutional neural network (CNN) that predicts the magnetic properties directly from the domain images with a high level of accuracy (maximum 93.9%). Our work has immense importance in promoting the applications of image regression methods through the CNN in understanding integral magnetic properties obtained from the microscopic features subject to change under external perturbations.Peer reviewe