Characterizing Atomistic Transitions Using Cross-scale Graph-pooled Chebyshev Signatures

TL;DR

This paper introduces a novel graph-based signature method for analyzing atomistic transitions in large-scale simulations, enabling classification and clustering of complex structural changes.

Contribution

It presents a new permutation-invariant signature technique using cross-scale graph pooling and Chebyshev operators to characterize atomistic transitions.

Findings

Signatures effectively classify transition types in nanoparticle simulations.

The method captures complex hierarchical patterns beyond traditional techniques.

It enables natural distance metrics for transition comparison.

Abstract

Large-scale atomistic simulations can produce extreme volumes of information in the form of long trajectories. Reliably and automatically extracting key information from such datasets remains a formidable challenge, especially as it pertains to the analysis of the structural transitions affecting the system. We present a novel approach to characterize and compare atomistic transitions using cross-scale graph-pooled Chebyshev signatures. These signatures are permutation invariants of an operator that transform a Coulomb matrix representation of the initial state of the system into that corresponding to the final state. Using a long-time trajectory of a small metallic nanoparticle, we show that these signatures can be used to define a natural distance metric between transitions that allows for classification and clustering into physically meaningful families. This approach is shown to capture complex patterns and hierarchies of transition types that are inaccessible to traditional techniques, dramatically facilitating the analysis of large-scale simulations.