Abstract
Actinide and lanthanide-based materials display exotic properties that originate from the presence of itinerant or localized f electrons and include unconventional superconductivity and magnetism, hidden order, and heavy-fermion behavior. Due to the strongly correlated nature of the 5f electrons, magnetic properties of these compounds depend sensitively on applied magnetic field and pressure, as well as on chemical doping. However, precise connection between the structure and magnetism in actinide-based materials is currently unclear. In this investigation, we established such structure-property links by assembling and mining two datasets that aggregate, respectively, the results of high-throughput density functional theory simulations and experimental measurements for the families of uranium- and neptunium-based binary compounds. Various regression algorithms were utilized to identify correlations among accessible attributes (features or descriptors) of the material systems and predict their cation magnetic moments and general forms of magnetic ordering. Descriptors representing compound structural parameters and cation f-subshell occupation numbers were identified as most important for accurate predictions. The best machine learning model developed employs the random forest regression algorithm. It can predict both spin and orbit moment size with root-mean-square error of 0.17μB and 0.19μB, respectively. The random forest classification algorithm is used to predict the ordering (paramagnetic, ferromagnetic, and antiferromagnetic) of such systems with 76% accuracy.
Original language | English |
---|---|
Article number | 064414 |
Journal | Physical Review Materials |
Volume | 4 |
Issue number | 6 |
DOIs | |
State | Published - Jun 2020 |
Externally published | Yes |
Funding
A.G. acknowledges the hospitality of Los Alamos National Laboratory, where this project was initialized. She is also thankful to Dr. L. Louis, D. P. Trujillo, Dr. G. Pilania, and Dr. G. P. F. Wood for their helpful contributions to code development and discussions on implementation of various machine learning techniques. This work was supported by the U. S. DOE NNSA under Contract No. 89233218CNA000001 through the Rapid Response Program of Institute for Materials Science at LANL (A.G.), by the DOE BES “Quantum Fluctuations in Narrow-Band System” Project (F.R), and the NNSA Advanced Simulation and Computing Program (J.-X.Z.). It was supported in part through the Center for Integrated Nanotechnologies, a U. S. DOE Office of Basic Energy Sciences user facility in partnership with the LANL Institutional Computing Program for computational resources.
Funders | Funder number |
---|---|
U. S. DOE NNSA | 89233218CNA000001 |
Basic Energy Sciences | |
National Nuclear Security Administration |