Atomistic simulation of solid-solid phase transition from machine learning force fields

We present an efficient framework that combines machine learning potential (MLP) and advanced sampling techniques to investigate solid-solid phase transition. To achive this goal, we have developed a scalable MLP model to warrant an accurate interpolation of the energy surface where more than two solid phases coexist. In this presetation, two application examples will be discussed. We first combine the MLP with metadynamics simulation to investigate the phase transition of GaN under high pressure with different model sizes, in which we observe the sequential change of transition mechanism from collective modes to nucleation and growths. Such a mechanism change highlights the importance of statistical sampling with large system size. Secondly, we combine MLP with Monte Carlo simulation to elucidate the short range ordering on the NbMoTaW multi-principal element alloy (MPEA). The results show the strong attraction among Mo-Ta pairs forming the local ordered B2 structures. In addition, the property simulation results suggest that SRO increases the elastic constants and high-frequency phonon modes as well as introduces extra lattice friction of dislocation motion. This approach enables a rapid compositional screening and paves the way for computation-guided materials design of new MPEAs with better performance.