Phonon-informed Crystal Structure Classification via Precision-Adaptive ResNet-based Confidence Ensemble

TL;DR

This paper introduces a phonon-informed, ensemble deep learning framework that enhances crystal structure classification accuracy, robustness, and high-throughput capability by integrating multiple descriptors and adaptive confidence measures.

Contribution

It presents a novel multi-descriptor, confidence-adaptive ResNet-based ensemble method for classifying crystal structures from phonon and spectral data, improving robustness and automation.

Findings

Achieved high accuracy in classifying over 19,000 crystals into structural prototypes.

Demonstrated robustness across crystals of varying quality and size.

Enabled high-throughput, automated material structure analysis.

Abstract

Accurate description of crystal structures is a prerequisite for predicting the physicochemical properties of materials. However, conventional X-ray diffraction (XRD) characterization often encounters intrinsic bottlenecks when applied to complex multiphase systems, necessitating the integration of complementary optical measurement. In this study, we developed a multi-descriptor framework by integrating key parameters including space groups, Pearson symbols, and Wyckoff sequences, to categorize the dataset of over 19,000 crystals into several dozen structural prototypes. Then, an accuracy-adaptive ensemble network based on residual architectures was implemented to capture structural ``fingerprints" within phonon vibration modes and Raman spectra. The ensemble algorithm demonstrates exceptional robustness when processing various crystals of varying lengths and quality. This data-driven classification strategy not only overcomes the reliance of traditional characterization on ideal data but also provides a high-throughput tool for the automated analysis of material structures in large-scale experimental workflows.