1. Application of Bayesian Optimization and Regression Analysis to Ferromagnetic Materials Development
- Author
-
Nian X. Sun, Huaihao Chen, Cunzheng Dong, Peter D. Tonner, Xianfeng Liang, Alexandria Will-Cole, and A. Gilad Kusne
- Subjects
Computer science ,Bayesian optimization ,Magnetostriction ,Regression analysis ,Function (mathematics) ,Ferromagnetic resonance ,Field (computer science) ,Electronic, Optical and Magnetic Materials ,Condensed Matter::Materials Science ,symbols.namesake ,Surrogate model ,symbols ,Electrical and Electronic Engineering ,Gaussian process ,Algorithm - Abstract
Bayesian optimization is a well-developed machine learning field for black box function optimization. In Bayesian optimization a surrogate predictive model, here a Gaussian process, is used to approximate the black box function. The estimated mean and uncertainty of the surrogate model are paired with an acquisition function to decide where to sample next. In this study we applied this technique to known ferromagnetic thin film materials such as ferromagnetic (Fe100-y Gay)1-xBx (x=0 to 21 & y=9 to 17) and (Fe100-y Gay)1-xCx (x=1 to 26 and y=2 to 18) to demonstrate optimization of structure-property relationships, specifically the dopant concentration or stoichiometry effect on magnetostriction and ferromagnetic resonance linewidth. Our results demonstrated that Bayesian optimization can be deployed to optimize structure-property relationships in FeGaB and FeGaC thin films. We have shown through simulation that using Bayesian optimization methods to guide experiments reduced the number of samples required to statistically determine the maximum or minimum by 50 % compared to traditional methods. Our results suggest that Bayesian optimization can be used to save time and resources to optimize ferromagnetic films. This method is transferrable to other ferromagnetic material structure-property relationships, providing an accessible implementation of machine learning to magnetic materials development.
- Published
- 2022
- Full Text
- View/download PDF