Learning Nonlocal Interactions in Large-Scale Heterogeneous Metamaterials through Scientific Machine Learning
Abstract
In multiscale systems, nonlocal interactions among spatially distributed constituents can unlock collective, potentially emergent behavior irreducible to individual constituent responses. Beyond characterization, nonlocality in multiscale systems is increasingly viewed as a design element across fracture mechanics, wave physics, and disordered systems. Existing nonlocality theories provide rigorous descriptions and mechanistic insight, but often require prescribed analytic forms, range, symmetries, or periodicity. Machine learning offers a data-driven route to learn interactions, yet principled approaches that tie the network design to physical theory remain nascent. Here we present domain-decomposition attention neural operator (DANO), which learns configuration-dependent interactions in heterogeneous systems governed by linear field equations from field data alone. Through a case study in large-scale optical metasurfaces, we demonstrate DANO's full-field prediction under geometric heterogeneity and across drive conditions, small-to-large domain transfer, and multifunctional inverse design, with learned interactions validated through physics-based interrogation. As an AI-for-Science tool, it supports interaction discovery and scalable, customizable design of nonlocal multiscale systems, including virtual-reality optics.
Related
- Effective-action formulation of k-odd bianisotropy and unidirectional polarization rotation in nonlocal temporal metamaterials
- Asymmetric Negative Refraction in Nonlocal Double-Wire Metamaterials
- Towards Large-Scale Heterogeneous Data Organization for Scientific Foundation Models: A Nuclear Fusion Case Study
- A foundation model for energy and radiation systems built on heterogeneous scientific interfaces
- Comment on "Space-time shifted solitons and solution interactions for a generalized nonlocal nonlinear Schrödinger equation"
BibTeX
@misc{lee2026learning,
title = {{Learning Nonlocal Interactions in Large-Scale Heterogeneous Metamaterials through Scientific Machine Learning}},
author = {Dex Doksoo Lee and Jehyeon Shin and Yue Yu and Sunkyu Yu and Junsuk Rho and Wei Chen},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.41887},
eprint = {2610.41887},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.41887},
}
RIS
TY - UNPB
TI - Learning Nonlocal Interactions in Large-Scale Heterogeneous Metamaterials through Scientific Machine Learning
AU - Dex Doksoo Lee
AU - Jehyeon Shin
AU - Yue Yu
AU - Sunkyu Yu
AU - Junsuk Rho
AU - Wei Chen
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2610.41887
UR - https://arxiv.org/abs/2610.41887
AB - In multiscale systems, nonlocal interactions among spatially distributed constituents can unlock collective, potentially emergent behavior irreducible to individual constituent responses. Beyond characterization, nonlocality in multiscale systems is increasingly viewed as a design element across fracture mechanics, wave physics, and disordered systems. Existing nonlocality theories provide rigorous descriptions and mechanistic insight, but often require prescribed analytic forms, range, symmetries, or periodicity. Machine learning offers a data-driven route to learn interactions, yet principled approaches that tie the network design to physical theory remain nascent. Here we present domain-decomposition attention neural operator (DANO), which learns configuration-dependent interactions in heterogeneous systems governed by linear field equations from field data alone. Through a case study in large-scale optical metasurfaces, we demonstrate DANO's full-field prediction under geometric heterogeneity and across drive conditions, small-to-large domain transfer, and multifunctional inverse design, with learned interactions validated through physics-based interrogation. As an AI-for-Science tool, it supports interaction discovery and scalable, customizable design of nonlocal multiscale systems, including virtual-reality optics.
ER -