![](https://d3ilqtpdwi981i.cloudfront.net/C8engm3XhXnU4TiTCk5vs1pOPbA=/425x550/smart/https://bepress-attached-resources.s3.amazonaws.com/uploads/e0/a4/8e/e0a48ef4-ccb7-4668-85d1-a6beac9741e1/thumbnail_b5719d54-cfd3-4fd2-8777-28147c77705c.jpg)
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.
Available at: http://works.bepress.com/peter-orth/45/