Machine learning force-field model for kinetic Monte Carlo simulations of itinerant Ising magnets
This work addresses the problem of prohibitive computational costs for researchers simulating itinerant electron systems, offering a scalable ML framework that is incremental in applying existing ML force-field concepts to a new domain.
The authors tackled the computational bottleneck of repeated electronic structure calculations in kinetic Monte Carlo simulations of itinerant Ising magnets by developing a scalable convolutional neural network model to predict local fields and energy changes, enabling large-scale simulations that uncovered unusual ferromagnetic domain coarsening at low temperatures.
We present a scalable machine learning (ML) framework for large-scale kinetic Monte Carlo (kMC) simulations of itinerant electron Ising systems. As the effective interactions between Ising spins in such itinerant magnets are mediated by conducting electrons, the calculation of energy change due to a local spin update requires solving an electronic structure problem. Such repeated electronic structure calculations could be overwhelmingly prohibitive for large systems. Assuming the locality principle, a convolutional neural network (CNN) model is developed to directly predict the effective local field and the corresponding energy change associated with a given spin update based on Ising configuration in a finite neighborhood. As the kernel size of the CNN is fixed at a constant, the model can be directly scalable to kMC simulations of large lattices. Our approach is reminiscent of the ML force-field models widely used in first-principles molecular dynamics simulations. Applying our ML framework to a square-lattice double-exchange Ising model, we uncover unusual coarsening of ferromagnetic domains at low temperatures. Our work highlights the potential of ML methods for large-scale modeling of similar itinerant systems with discrete dynamical variables.