Accelerating phase-field based predictions via surrogate models trained by machine learning methods.

The phase-field method is a powerful and versatile computational approach for modeling the evolution of microstructures and associated properties for a wide variety of physical, chemical and biological systems. However, existing high-fidelity phase-field models are inherently computationally expensive, requiring high-performance computing resources and sophisticated numerical integration schemes to achieve a useful degree of accuracy. In this presentation, I will present a computationally inexpensive, accurate, data-driven surrogate model that directly learns the microstructural evolution of targeted systems by combining phase-field and history-dependent machine-learning techniques. The methodology consists of integrating a statistically-representative, low-dimensional description of the microstructure, obtained directly from phase-field simulations, with either a Time-Series Multivariate Adaptive Regression Splines autoregressive algorithm or a Long Short-Term Memory neural network. I will show that the neural-network-trained surrogate model exhibits the best performance and accurately predicts the nonlinear microstructure evolution of a two-phase mixture during spinodal decomposition in seconds, without the need for “on-the-fly” solutions of the phase-field equations-of-motion. I will also show that the predictions from our machine-learned surrogate model can be fed directly as an input into a classical high-fidelity phase-field model in order to accelerate the high-fidelity phase-field simulations by leaping in time. Such machine-learned phase-field framework opens a promising path forward to novel uses of predictive modeling algorithms for discovering, understanding, and predicting processing-microstructureperformance relationships.