Search

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. [ABSTRACT FROM AUTHOR]

[Display omitted] • Predicting microstructural evolution of polymer blends by data-driven model. • Extending the model to predict microphase separation of block copolymers. • Inferring growth law of phase-separated structures from data-driven model. As emerging concepts, leveraging physical information with machine learning to construct hybrid models enables a scientific data-driven paradigm for the investigation of complex kinetic issues in the field of polymer science. Herein, the model of physics-informed neural networks (PINNs), integrating advantages of neural networks with physics-based knowledge, is extended to predict the spatiotemporal patterns of phase-separated microstructures of multicomponent polymers. It is demonstrated that the PINN-based data-driven model can achieve the forward, backward and bidirectional predictions of spatiotemporally phase-separated patterns of homopolymer blends. All predicted patterns reveal a high accuracy and robustness of PINN-based data-driven model by leveraging a small amount of training data. Particularly, the PINN-based method can be harnessed to infer the latent physical law about the growth kinetics of phase-separated microstructures. In addition, PINN-based data-driven model can also be generalized to forecast the spatiotemporal patterns of microphase-separated nanostructures of block copolymers and infer their growth kinetics. Our study opens the possibility of learning non-equilibrium phenomena of complex polymer systems from only a few snapshots of microstructural evolution. [ABSTRACT FROM AUTHOR]