Understanding Magnetic Properties of Uranium-Based Binary Compounds from Machine Learning

ORAL

Abstract

Actinide- and lanthanide-based materials constitute an important playground for exploring exotic properties stemming from the presence of itinerant or localized f-electrons. For example, uranium-based compounds have exhibited emergent phenomena, including magnetism, unconventional superconductivity, hidden order, and heavy fermion behavior. Among them, the magnetic properties with varying ordered states and moment size are sensitively dependent on pressure, chemical doping and magnetic field due to the strong-correlation effects on 5f-electrons. So far, there have even been no reports of systematic studies to map out connections between structures and properties of these compounds. In order to investigate such links and bridge between theoreotical and experimental learnings, we have constructed two databases combining results of high-throughput DFT simulations and experimental measurements, respectively, for a family of uranium-based binary compounds. We then utilized different machine learning models to identify related accessible attributes (features) and predict magnetic moments and ordering in these compounds.

–

Presenters

  • Ayana Ghosh

    Materials Science and Engineering, University of Connecticut

Authors

  • Ayana Ghosh

    Materials Science and Engineering, University of Connecticut

  • Serge M Nakhmanson

    Department of Materials Science and Engineering, University of Connecticut, Materials Science and Engineering, University of Connecticut

  • Jian-Xin Zhu

    Theoretical Division, Los Alamos National Laboratory, Los Alamos National Laboratory, Theoretical Division and Center for Integrated Nanotechnologies, Los Alamos National Laboratory, T4-PHYS OF CONDENSED MATTER & COMPLEX SYS, Los Alamos National Laboratory, Los aAlamos, USA, CINT, Los Alamos National Laboratory, Center for Integrated Nanotechnologies, Los Alamos National Laboratory, Los Alamos National Laboratory,