Diffusion-based Generative Machine Learning Model for Predicting Crack Propagation in Aluminum Nitride at the Atomic Scale

TL;DR

This paper introduces a diffusion-based machine learning model that predicts atomic-scale crack propagation in aluminum nitride efficiently, accurately capturing complex fracture behaviors without relying on traditional computationally expensive methods.

Contribution

The study presents a novel diffusion-based generative model trained on MD data that predicts crack evolution in AlN, bypassing the need for stress or energy inputs and generalizing to complex crack scenarios.

Findings

Achieves significant speedup over molecular dynamics simulations.

Accurately reproduces crack initiation, branching, and bridging mechanisms.

Generalizes to unseen multi-crack configurations.

Abstract

Predicting atomic-scale crack propagation in aluminum nitride (AlN) is critical for semiconductor reliability but remains prohibitively expensive via molecular dynamics (MD). We develop a diffusion-based generative machine learning model to predict atomic-scale crack propagation in AlN, a critical semiconductor material, by conditioning solely on initial microstructure embeddings. Trained on MD simulations of single-crack systems, the model achieves a significant speedup while accurately forecasting dynamic fracture processes, including stress-driven crack initiation, crack branching, and atomic-scale bridging ligaments. Crucially, it demonstrates inherent physical fidelity by reproducing material-intrinsic mechanisms while disregarding periodic boundary artifacts, and generalizes to unseen multi-crack configurations. Validation against MD ground truth confirms the capability of the model to capture complex fracture physics without auxiliary stress or energy data, enabling rapid exploration of crack-mediated failure for semiconductor reliability optimization.