Accelerating Phase Field Simulations Through a Hybrid Adaptive Fourier Neural Operator with U-Net Backbone

Abstract

Prolonged contact between a corrosive liquid and metal alloys can cause progressive dealloying. For such liquid-metal dealloying (LMD) process, phase field models have been developed. However, the governing equations often involve coupled non-linear partial differential equations (PDE), which are challenging to solve numerically. In particular, stiffness in the PDEs requires an extremely small time steps (e.g. $10^{-12}$ or smaller). This computational bottleneck is especially problematic when running LMD simulation until a late time horizon is required. This motivates the development of surrogate models capable of leaping forward in time, by skipping several consecutive time steps at-once. In this paper, we propose U-Shaped Adaptive Fourier Neural Operators (U-AFNO), a machine learning (ML) model inspired by recent advances in neural operator learning. U-AFNO employs U-Nets for extracting and reconstructing local features within the physical fields, and passes the latent space through a vision transformer (ViT) implemented in the Fourier space (AFNO). We use U-AFNOs to learn the dynamics mapping the field at a current time step into a later time step. We also identify global quantities of interest (QoI) describing the corrosion process (e.g. the deformation of the liquid-metal interface) and show that our proposed U-AFNO model is able to accurately predict the field dynamics, in-spite of the chaotic nature of LMD. Our model reproduces the key micro-structure statistics and QoIs with a level of accuracy on-par with the high-fidelity numerical solver. We also investigate the opportunity of using hybrid simulations, in which we alternate forward leap in time using the U-AFNO with high-fidelity time stepping. We demonstrate that while advantageous for some surrogate model design choices, our proposed U-AFNO model in fully auto-regressive settings consistently outperforms hybrid schemes.

References in corpus (20)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Fourier Neural Operator for Parametric Partial Differential Equations
• Phase-Field Formulation for Quantitative Modeling of Alloy Solidification
• FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
• A physics-informed variational DeepONet for predicting the crack path in brittle materials
• Adaptive Mesh Refinement Computation of Solidification Microstructures using Dynamic Data Structures
• Finite volume POD-Galerkin stabilised reduced order methods for the parametrised incompressible Navier-Stokes equations
• DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks
• Long-term predictions of turbulence by implicit U-Net enhanced Fourier neural operator
• Topological Control of Liquid-Metal-Dealloyed Structures
• Convolutional Neural Operators for robust and accurate learning of PDEs
• GPLaSDI: Gaussian Process-based Interpretable Latent Space Dynamics Identification through Deep Autoencoder
• Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers
• Grain Boundary Effects in Dealloying Metals: A Multi-Phase Field Study
• Microstructural pattern formation during liquid metal dealloying: Phase-field simulations and theoretical analyses
• Real-time Inference and Extrapolation via a Diffusion-inspired Temporal Transformer Operator (DiTTO)
• A Comprehensive Review of Latent Space Dynamics Identification Algorithms for Intrusive and Non-Intrusive Reduced-Order-Modeling
• DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training