Unsupervised Machine-Learning Pipeline for Data-Driven Defect Detection and Characterisation: Application to Displacement Cascades

TL;DR

This paper introduces an unsupervised machine learning pipeline that detects and characterizes atomic defects from molecular dynamics data, providing a comprehensive, threshold-free analysis of irradiation-induced damage in materials.

Contribution

The work presents a novel unsupervised ML workflow combining autoencoders, UMAP, and HDBSCAN to identify and classify defects directly from atomic simulation data, without prior templates or thresholds.

Findings

Successfully identifies defect outliers with 99.7% accuracy

Clusters defect types correlating with physical defect motifs

Achieves high correlation (R2 > 0.89) between defect counts and cluster sizes

Abstract

Neutron irradiation produces, within a few picoseconds, displacement cascades that are sequences of atomic collisions generating point and extended defects which subsequently affects the long-term evolution of materials. The diversity of these defects, characterized morphologically and statistically, defines what is called the "primary damage". In this work, we present a fully unsupervised machine learning (ML) workflow that detects and classifies these defects directly from molecular dynamics data. Local environments are encoded by the Smooth Overlap of Atomic Positions (SOAP) vector, anomalous atoms are isolated with autoencoder neural networks (AE), embedded with Uniform Manifold Approximation and Projection (UMAP) and clustered using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). Applied to 80 keV displacement cascades in Ni, Fe$_7$0Ni$_{10}$Cr$_{20}$, and Zr, the AE successfully identify the small fraction of outlier atoms that participate in defect formation. HDBSCAN then partitions the UMAP latent space of AE-flagged SOAP descriptors into well defined groups representing vacancy- and interstitial-dominated regions and, within each, separates small from large aggregates, assigning 99.7 % of outliers to compact physical motifs. A signed cluster-identification score confirms this separation, and cluster size scales with net defect counts (R2 > 0.89). Statistical cross analyses between the ML outlier map and several conventional detectors (centrosymmetry, dislocation extraction, etc.) reveal strong overlap and complementary coverage, all achieved without template or threshold tuning. This ML workflow thus provides an efficient tool for the quantitative mapping of structural anomalies in materials, particularly those arising from irradiation damage in displacement cascades.