Data‐Driven Design for Metamaterials and Multiscale Systems: A Review

Abstract

Metamaterials are artificial materials designed to exhibit effective material parameters that go beyond those found in nature. Composed of unit cells with rich designability that are assembled into multiscale systems, they hold great promise for realizing next‐generation devices with exceptional, often exotic, functionalities. However, the vast design space and intricate structure–property relationships pose significant challenges in their design. A compelling paradigm that could bring the full potential of metamaterials to fruition is emerging: data‐driven design. This review provides a holistic overview of this rapidly evolving field, emphasizing the general methodology instead of specific domains and deployment contexts. Existing research is organized into data‐driven modules, encompassing data acquisition, machine learning‐based unit cell design, and data‐driven multiscale optimization. The approaches are further categorized within each module based on shared principles, analyze and compare strengths and applicability, explore connections between different modules, and identify open research questions and opportunities.

AI-Based Metamaterial Design

“…The advantage of AI is not only restricted to design but also to fast analysis of medical data. This can be beneficial, especially in a hospital setting to fast-track patient care or improve time-dependent analysis . Xie et al have reported an FC-NN model for analyzing the CD response of chiral plasmonic metamaterials .…”

“…This can be beneficial, especially in a hospital setting to fast-track patient care or improve time-dependent analysis. 41 Xie et al have reported an FC-NN model for analyzing the CD response of chiral plasmonic metamaterials. 232 A permutation importance method (PIM) analysis was utilized to detect which parameters have the largest effect on CD response.…”

“…The frameworks usually involve initial training in which computational models learn the desired properties of the metamaterial and its structural parameters, thus generating new designs or optimizing existing ones to achieve specific objectives. , Regression and probabilistic algorithms evaluate complex structures and combinations of unit materials, while probability algorithms are primarily utilized for designing novel metamaterials. , The literature contains three subcategories of AI usage in metamaterial design: data analysis, algorithm development, and model evaluation. , Before any AI-based application, data sets undergo data preprocessing and assessment. Raw data in metamaterials are often harvested from experimental or numerical simulations and can be incomplete or inconsistent, or contain background noise . Data preprocessing such as cleaning is commonly used to rearrange and compose relevant sections of data.…”

“…Raw data in metamaterials are often harvested from experimental or numerical simulations and can be incomplete or inconsistent, or contain background noise. 41 Data preprocessing such as cleaning is commonly used to rearrange and compose relevant sections of data. Incomplete and noisy data can be cleaned via ML.…”