Machine learning force-field models for metallic spin glass
This work addresses the challenge of large-scale dynamical simulations for metallic spin glass systems, which is incremental as it adapts existing ML methods to incorporate spin degrees of freedom.
The authors tackled the problem of simulating metallic spin glasses by developing a scalable machine learning force-field model that predicts electron-induced local magnetic fields, enabling large-scale dynamical modeling of itinerant magnets with quenched disorder.
Metallic spin glass systems, such as dilute magnetic alloys, are characterized by randomly distributed local moments coupled to each other through a long-range electron-mediated effective interaction. We present a scalable machine learning (ML) framework for dynamical simulations of metallic spin glasses. A Behler-Parrinello type neural-network model, based on the principle of locality, is developed to accurately and efficiently predict electron-induced local magnetic fields that drive the spin dynamics. A crucial component of the ML model is a proper symmetry-invariant representation of local magnetic environment which is direct input to the neural net. We develop such a magnetic descriptor by incorporating the spin degrees of freedom into the atom-centered symmetry function methods which are widely used in ML force-field models for quantum molecular dynamics. We apply our approach to study the relaxation dynamics of an amorphous generalization of the s-d model. Our work highlights the promising potential of ML models for large-scale dynamical modeling of itinerant magnets with quenched disorder.