From Local Atomic Motifs to Thermodynamic State: An Interpretable Physics-Informed Framework for Cu-Zr Metallic Glasses
Abstract
Machine-learning models that relate local atomic structure to the thermodynamic state of metallic glasses typically assess physical consistency after training rather than enforcing it during learning. Here, we develop a multi-task physics-informed neural network (PINN) that predicts temperature directly from Voronoi-motif population histograms while incorporating autograd-derived gradient constraints representing physically motivated relationships between structural motifs, quench rate, and temperature. The model simultaneously classifies each configuration as liquid, supercooled/transition, or glass through an auxiliary classification head. The classification task achieves 96.6% test accuracy with a macro-F1 score of 0.95, while the regression head yields a mean absolute error of 23.4 K on a trajectory-disjoint held-out test set. Five-fold trajectory-grouped cross-validation, deep-ensemble predictions, and Monte Carlo dropout are used to assess model robustness and predictive uncertainty. Sensitivity analyses demonstrate that physics constraints can be incorporated over a broad range of loss weights without compromising predictive accuracy, while substantially improving compliance with the prescribed physical trends. Benchmarking against conventional machine-learning regressors further demonstrates competitive predictive performance. SHAP analysis across the cross-validation ensemble identifies the coupled near-icosahedral motif family, particularly the full icosahedral motif and its single-atom-perturbed counterpart, as the dominant structural fingerprints of the glassy state. These results demonstrate that physically motivated constraints can be embedded directly into motif-based structure-property models, providing a pathway from post-hoc interpretability toward physically constrained machine learning for metallic glasses.
Related
- Physics-informed interpretable forms for dipole resonances and quantities relevant for astrophysics
- PINNIES: An efficient physics-informed neural network framework for integral operator problems
- Pretrain finite element method: A pretraining and warm-start framework for PDEs via physics-informed neural operators
- A Framework Integrating the Dynamic Stiffness Matrix with Physics-Informed Neural Networks for Solving Eigenvalue Problems and Analysing Dynamic Response
- Development of a Physics-Informed Neural Framework, MEOWN, for Rapid Prediction of Muon Stopping Sites in Crystalline Materials, for understanding Quantum Magnet employing Muon Spectroscopy
BibTeX
@misc{joshi2026from,
title = {{From Local Atomic Motifs to Thermodynamic State: An Interpretable Physics-Informed Framework for Cu-Zr Metallic Glasses}},
author = {Prashil S. Joshi},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.22992},
eprint = {2609.22992},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.22992},
}
RIS
TY - UNPB
TI - From Local Atomic Motifs to Thermodynamic State: An Interpretable Physics-Informed Framework for Cu-Zr Metallic Glasses
AU - Prashil S. Joshi
PY - 2026
DA - 2026/09/19
PB - arXiv
DO - 10.48550/arxiv.2609.22992
UR - https://arxiv.org/abs/2609.22992
AB - Machine-learning models that relate local atomic structure to the thermodynamic state of metallic glasses typically assess physical consistency after training rather than enforcing it during learning. Here, we develop a multi-task physics-informed neural network (PINN) that predicts temperature directly from Voronoi-motif population histograms while incorporating autograd-derived gradient constraints representing physically motivated relationships between structural motifs, quench rate, and temperature. The model simultaneously classifies each configuration as liquid, supercooled/transition, or glass through an auxiliary classification head. The classification task achieves 96.6% test accuracy with a macro-F1 score of 0.95, while the regression head yields a mean absolute error of 23.4 K on a trajectory-disjoint held-out test set. Five-fold trajectory-grouped cross-validation, deep-ensemble predictions, and Monte Carlo dropout are used to assess model robustness and predictive uncertainty. Sensitivity analyses demonstrate that physics constraints can be incorporated over a broad range of loss weights without compromising predictive accuracy, while substantially improving compliance with the prescribed physical trends. Benchmarking against conventional machine-learning regressors further demonstrates competitive predictive performance. SHAP analysis across the cross-validation ensemble identifies the coupled near-icosahedral motif family, particularly the full icosahedral motif and its single-atom-perturbed counterpart, as the dominant structural fingerprints of the glassy state. These results demonstrate that physically motivated constraints can be embedded directly into motif-based structure-property models, providing a pathway from post-hoc interpretability toward physically constrained machine learning for metallic glasses.
ER -