Learning crystal field parameters using convolutional neural networks

TL;DR

This paper introduces a deep learning approach using convolutional neural networks to accurately extract crystal field parameters from thermodynamic data of rare-earth magnetic materials, streamlining the analysis process.

Contribution

The study develops and applies a CNN-based method to determine crystal field parameters from thermodynamic data, avoiding complex multi-parameter fitting.

Findings

CNN accurately extracts CF parameters from synthetic data.

Method successfully applied to experimental data of specific compounds.

Approach works across various symmetries and angular momentum values.

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.