Neutron and X-ray Diffraction Reveal the Limits of Long-Range Machine Learning Potentials for Medium-Range Order in Silica Glass

2026-04-22

AI Summary

Accurately predicting the medium-range order (MRO) in vitreous silica remains a key challenge for machine learning interatomic potentials (MLIPs). This work integrates neutron and X-ray diffraction experiments to develop a short-range model based on MACE and a long-range model incorporating reciprocal-space gated attention, enabling large-scale molecular dynamics simulations to probe MRO formation mechanisms. The study provides the first experimental validation that neither purely local interactions nor simple inclusion of long-range terms can faithfully reproduce MRO, highlighting the necessity of training data and sampling strategies that span the entire liquid-to-glass transition. It is found that the short-range model over-structures the network, yielding an exaggerated first sharp diffraction peak (FSDP), while the long-range model improves liquid-state structure but still deviates from experimental glass configurations—both limited by insufficient network flexibility, leading to unphysical medium-range arrangements.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Other Foundations of Computer Vision
• Multiagent Systems: Other Foundations of Multi Agent Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Glassy silica is a foundational material in optics and electronics, yet accurately predicting its medium-range order (MRO) remains a major challenge for machine-learning interatomic potentials (MLIPs). While local MLIPs reproduce the short-range SiO4 tetrahedral network well, it remains unclear whether locality alone is sufficient to recover the first sharp diffraction peak (FSDP), the principal experimental signature of MRO. Here, we combine neutron and X-ray diffraction measurements with large-scale molecular dynamics driven by two MACE-based models: a short-range (SR) potential and a long-range (LR) extension incorporating reciprocal-space gated attention. The SR model systematically over-structures the network, producing an overly intense FSDP in both the liquid and glassy states. Incorporating long-range interactions improves agreement with experiment for the liquid structure by reducing this excess ordering, but the LR model still fails to recover the experimental amorphous MRO after quenching. Ring-statistics and bond-angle analyses reveal that SR model exhibits an artificially narrow distribution dominated by six-membered rings, while the LR model produces a broader but still biased ring population. Despite preserving the correct tetrahedral geometry, both models show limited variability in Si-O-Si angles, indicating constrained network flexibility. These structural signatures demonstrate that both models retain excessive memory of the parent liquid network, leading to kinetically trapped and nonphysical medium-range configurations during vitrification. These results show that explicit long-range interactions are necessary but not sufficient for predictive modelling of disordered silica and suggest that accurate MRO further requires training data and sampling strategies that adequately represent the liquid-to-glass transition.

Problem

• medium-range order
• machine learning interatomic potentials
• silica glass
• first sharp diffraction peak
• liquid-to-glass transition

Innovation

• medium-range order
• machine-learning interatomic potentials
• first sharp diffraction peak
• long-range interactions
• vitrification