Inferring the Physics of Structural Evolution of Multicomponent Polymers via Machine-Learning-Accelerated Method

Dynamic self-consistent field theory (DSCFT) is a fruitful approach for modeling the structural evolution and collective kinetics for a wide variety of multicomponent polymers. However, solving a set of DSCFT equations remains daunting because of high computational demand. Herein, a machine learning method, integrating low-dimensional representations of microstructures and long short-term memory neural networks, is used to accelerate the predictions of structural evolution of multicomponent polymers. It is definitively demonstrated that the neural-network-trained surrogate model has the capability to accurately forecast the structural evolution of homopolymer blends as well as diblock copolymers, without the requirement of “on-the-fly” solution of DSCFT equations. Importantly, the data-driven method can also infer the latent growth laws of phase-separated microstructures of multicomponent polymers through simply using a few of time sequences from their past, without the prior knowledge of the governing dynamics. Our study exemplifies how the machine-learning-accelerated method can be applied to understand and discover the physics of structural evolution in the complex polymer systems.