TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.11.1.011
TI  - Learning crystal field parameters using convolutional neural networks
PY  - 2021/07/14
UR  - https://scipost.org/SciPostPhys.11.1.011
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 11
IS  - 1
SP  - 011
A1  - Berthusen, Noah F.
AU  - Sizyuk, Yuriy
AU  - Scheurer, Mathias S.
AU  - Orth, Peter P.
AB  - 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.
ER  -

@Article{10.21468/SciPostPhys.11.1.011,
	title={{Learning crystal field parameters using convolutional neural networks}},
	author={Noah F. Berthusen and Yuriy Sizyuk and Mathias S. Scheurer and Peter P. Orth},
	journal={SciPost Phys.},
	volume={11},
	pages={011},
	year={2021},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.11.1.011},
	url={https://scipost.org/10.21468/SciPostPhys.11.1.011},
}