Morphological evolution via surface diffusion learned by convolutional, recurrent neural networks: extrapolation and prediction uncertainty

Abstract

We use a Convolutional Recurrent Neural Network approach to learn morphological evolution driven by surface diffusion. To this aim we first produce a training set using phase field simulations. Intentionally, we insert in such a set only relatively simple, isolated shapes. After proper data augmentation, training and validation, the model is shown to correctly predict also the evolution of previously unobserved morphologies and to have learned the correct scaling of the evolution time with size. Importantly, we quantify prediction uncertainties based on a bootstrap-aggregation procedure. The latter proved to be fundamental in pointing out high uncertainties when applying the model to more complex initial conditions (e.g. leading to splitting of high aspect-ratio individual structures). Automatic smart-augmentation of the training set and design of a hybrid simulation method are discussed.

arXiv comment11 pages, 7 figures

References in corpus (16)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• A high-bias, low-variance introduction to Machine Learning for physicists
• Data-driven materials science: status, challenges and perspectives
• A neural network interatomic potential for the phase change material GeTe
• Deep Fluids: A Generative Network for Parameterized Fluid Simulations
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Machine learning materials physics: Surrogate optimization and multi-fidelity algorithms predict precipitate morphology in an alternative to phase field dynamics
• Comparison of phase-field models for surface diffusion
• Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures
• Data-driven simulation and characterisation of gold nanoparticle melting
• Doubly Degenerate Diffuse Interface Models of Surface Diffusion
• Modeling the Ga/As binary system across temperaturesand compositions from first principles
• Effect of Transport Mechanism on the Coarsening of Bicontinuous Structures: A Comparison between Bulk and Surface Diffusion
• Doubly Degenerate Diffuse Interface Models of Anisotropic Surface Diffusion

Cited by in corpus (2)

• Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks
• Extreme time extrapolation capabilities and thermodynamic consistency of physics-inspired Neural Networks for the 3D microstructure evolution of materials via Cahn-Hilliard flow