Teaching Artificial Intelligence to Perform Rapid, Resolution-Invariant Grain Growth Modeling via Fourier Neural Operator

2025-03-18

AI Summary

Phase-field modeling of microstructural evolution in polycrystalline systems suffers from high computational cost, while machine learning surrogates often exhibit strong resolution dependence and limited generalizability. To address these challenges, this work introduces the Fourier Neural Operator (FNO) — for the first time — into grain growth modeling, establishing a resolution-agnostic surrogate. The proposed model integrates the Fan–Chen phase-field dynamics with FNO’s global spectral-domain representation capability, enabling accurate long-term predictions independent of spatial discretization. It demonstrates robust generalization across unseen grid resolutions and novel initial grain configurations, achieving long-term prediction errors below 3.2%. Compared to conventional phase-field simulations, it reduces computational overhead significantly while preserving high fidelity. This framework establishes a new paradigm for efficient, robust, and scalable multiscale modeling of microstructural evolution in polycrystalline materials.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Microstructural evolution, particularly grain growth, plays a critical role in shaping the physical, optical, and electronic properties of materials. Traditional phase-field modeling accurately simulates these phenomena but is computationally intensive, especially for large systems and fine spatial resolutions. While machine learning approaches have been employed to accelerate simulations, they often struggle with resolution dependence and generalization across different grain scales. This study introduces a novel approach utilizing Fourier Neural Operator (FNO) to achieve resolution-invariant modeling of microstructure evolution in multi-grain systems. FNO operates in the Fourier space and can inherently handle varying resolutions by learning mappings between function spaces. By integrating FNO with the phase field method, we developed a surrogate model that significantly reduces computational costs while maintaining high accuracy across different spatial scales. We generated a comprehensive dataset from phase-field simulations using the Fan Chen model, capturing grain evolution over time. Data preparation involved creating input-output pairs with a time shift, allowing the model to predict future microstructures based on current and past states. The FNO-based neural network was trained using sequences of microstructures and demonstrated remarkable accuracy in predicting long-term evolution, even for unseen configurations and higher-resolution grids not encountered during training.

Problem

• Accelerate grain growth modeling using Fourier Neural Operator
• Overcome resolution dependence in microstructure evolution simulations
• Reduce computational costs while maintaining high accuracy

Innovation

• Fourier Neural Operator enables resolution-invariant modeling.
• Integration of FNO with phase field reduces computational costs.
• Model predicts future microstructures using time-shifted data.