Abstract
A data-driven framework is presented for building magneto-elastic machine-learning interatomic potentials (ML-IAPs) for large-scale spin-lattice dynamics simulations. The magneto-elastic ML-IAPs are constructed by coupling a collective atomic spin model with an ML-IAP. Together they represent a potential energy surface from which the mechanical forces on the atoms and the precession dynamics of the atomic spins are computed. Both the atomic spin model and the ML-IAP are parametrized on data from first-principles calculations. We demonstrate the efficacy of our data-driven framework across magneto-structural phase transitions by generating a magneto-elastic ML-IAP for α-iron. The combined potential energy surface yields excellent agreement with first-principles magneto-elastic calculations and quantitative predictions of diverse materials properties including bulk modulus, magnetization, and specific heat across the ferromagnetic–paramagnetic phase transition.
Highlights
Magnetism strongly influences thermomechanical properties in a large variety of materials, such as single-element magnetic metals[1,2], steels[3], high-entropy alloys[4,5], nuclear fuels such as uranium dioxide[6], magnetic oxides[7,8], and numerous other classes of functional materials[9]
Turning to spin-lattice dynamics calculations based on our magneto-elastic machine-learning interatomic potentials (ML-interatomic potentials (IAPs)), we assess the quantitative accuracy with respect to experimental measurements of changes in magnetic and thermoelastic properties as the material is heated
We presented a data-driven framework for automated generation of magneto-elastic machine learning (ML)-IAPs which enable large-scale spin-lattice dynamics simulations for any magnetic material in LAMMPS
Summary
Magnetism strongly influences thermomechanical properties in a large variety of materials, such as single-element magnetic metals[1,2], steels[3], high-entropy alloys[4,5], nuclear fuels such as uranium dioxide[6], magnetic oxides[7,8], and numerous other classes of functional materials[9]. All atomic configurations in the training set magneto-elastic ML-IAPs as they generate a consistent PES result from first-principles calculations performed with the same accurately representing the magnetic degrees of freedom and DFT setup Turning to spin-lattice dynamics calculations based on our magneto-elastic ML-IAP (as detailed in the “Methods” section), we assess the quantitative accuracy with respect to experimental measurements of changes in magnetic and thermoelastic properties as the material is heated. In making this comparison, it is necessary to choose which thermodynamic state variables will be held fixed and which will be allowed to vary with temperature. The dashed lines correspond to the DFT results, and the continuous lines to our classical model results, whereas the line
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
