A Novel Physics-Regularized Interpretable Machine Learning Model for Grain Growth

TL;DR

This paper introduces PRIMME, a physics-regularized deep learning model that accurately predicts grain growth behavior, bridging the gap between experimental observations and simulations without relying on explicit physical assumptions.

Contribution

The paper presents a novel deep learning framework that captures grain growth dynamics directly from data, integrating physics regularization for interpretability and improved accuracy.

Findings

PRIMME accurately replicates 2D normal grain growth.

The model's predictions align well with analytical and simulation results.

PRIMME demonstrates adaptability to irregular grain growth scenarios.

Abstract

Experimental grain growth observations often deviate from grain growth simulations, revealing that the governing rules for grain boundary motion are not fully understood. A novel deep learning model was developed to capture grain growth behavior from training data without making assumptions about the underlying physics. The Physics-Regularized Interpretable Machine Learning Microstructure Evolution (PRIMME) model consists of a multi-layer neural network that predicts the likelihood of a point changing to a neighboring grain. Here, we demonstrate PRIMME's ability to replicate two-dimensional normal grain growth by training it with Monte Carlo Potts simulations. The trained PRIMME model's grain growth predictions in several test cases show good agreement with analytical models, phase-field simulations, Monte Carlo Potts simulations, and results from the literature. Additionally, PRIMME's adaptability to investigate irregular grain growth behavior is shown. Important aspects of PRIMME like interpretability, regularization, extrapolation, and overfitting are also discussed.