Machine learning nonequilibrium phase transitions in charge-density wave insulators
This work addresses a computational bottleneck for simulating nonequilibrium dynamics in quantum materials, offering an efficient method for researchers in condensed matter physics and materials science, though it is incremental as it builds on existing force learning techniques.
The researchers tackled the high computational cost of simulating voltage-driven phase transitions in charge-density wave insulators by developing a machine learning framework that predicts electronic forces from lattice configurations, bypassing expensive nonequilibrium Green's function calculations. They demonstrated this approach on a Holstein model, achieving orders of magnitude gains in computational efficiency while quantitatively reproducing domain wall motion and phase transition dynamics.
Nonequilibrium electronic forces play a central role in voltage-driven phase transitions but are notoriously expensive to evaluate in dynamical simulations. Here we develop a machine learning framework for adiabatic lattice dynamics coupled to nonequilibrium electrons, and demonstrate it for a gating induced insulator to metal transition out of a charge density wave state in the Holstein model. Although exact electronic forces can be obtained from nonequilibrium Green's function (NEGF) calculations, their high computational cost renders long time dynamical simulations prohibitively expensive. By exploiting the locality of the electronic response, we train a neural network to directly predict instantaneous local electronic forces from the lattice configuration, thereby bypassing repeated NEGF calculations during time evolution. When combined with Brownian dynamics, the resulting machine learning force field quantitatively reproduces domain wall motion and nonequilibrium phase transition dynamics obtained from full NEGF simulations, while achieving orders of magnitude gains in computational efficiency. Our results establish direct force learning as an efficient and accurate approach for simulating nonequilibrium lattice dynamics in driven quantum materials.