Publication Date

7-14-2021

Department

Ames Laboratory; Electrical and Computer Engineering; Physics and Astronomy

Campus Units

Electrical and Computer Engineering, Physics and Astronomy, Ames Laboratory

OSTI ID+

1807978

Report Number

IS-J 10548

DOI

10.21468/SciPostPhys.11.1.011

Journal Title

SciPost Physics

Volume Number

11

Issue Number

1

First Page

011

Abstract

We present a deep machine learning algorithm to extract crystal field (CF) Stevens parameters from thermodynamic data of rare-earth magnetic materials. The algorithm employs a two-dimensional convolutional neural network (CNN) that is trained on magnetization, magnetic susceptibility and specific heat data that is calculated theoretically within the single-ion approximation and further processed using a standard wavelet transformation. We apply the method to crystal fields of cubic, hexagonal and tetragonal symmetry and for both integer and half-integer total angular momentum values J of the ground state multiplet. We evaluate its performance on both theoretically generated synthetic and previously published experimental data on CeAgSb 2 , PrAgSb 2 and PrMg 2 Cu 9 , and find that it can reliably and accurately extract the CF parameters for all site symmetries and values of J considered. This demonstrates that CNNs provide an unbiased approach to extracting CF parameters that avoids tedious multi-parameter fitting procedures.

DOE Contract Number(s)

AC02-07CH11358; DMR-2002850

Language

en

Publisher

Iowa State University Digital Repository, Ames IA (United States)

Share

COinS