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. In this review, we provide a holistic overview of this rapidly evolving field, emphasizing the general methodology instead of specific domains and deployment contexts. We organize existing research into data-driven modules, encompassing data acquisition, machine learning-based unit cell design, and data-driven multiscale optimization. We further categorize the approaches 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.

References in corpus (40)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Topology optimization based on moving deformable components: A new computational framework
• Training deep neural networks for the inverse design of nanophotonic structures
• A Generative Model for Inverse Design of Metamaterials
• Physics-informed neural networks for inverse problems in nano-optics and metamaterials
• Experiments on transformation thermodynamics: Molding the flow of heat
• Determinantal point processes for machine learning
• Programmable Mechanical Metamaterials
• On the feasibility of pentamode mechanical metamaterials
• The Joint Automated Repository for Various Integrated Simulations (JARVIS) for data-driven materials design
• Global optimization of dielectric metasurfaces using a physics-driven neural network
• A physics-informed variational DeepONet for predicting the crack path in brittle materials
• Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
• Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems
• Metasurface Broadband Solar Absorber
• Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures
• Machine-Learning-Assisted Metasurface Design for High-Efficiency Thermal Emitter Optimization
• Data-driven topology optimization of spinodoid metamaterials with seamlessly tunable anisotropy
• On the use of Artificial Neural Networks in Topology Optimisation
• Auxetic metamaterials from disordered networks
• Simulator-based training of generative models for the inverse design of metasurfaces
• Reliable extrapolation of deep neural operators informed by physics or sparse observations
• De-homogenization of optimal multi-scale 3D topologies
• Spider-Web Inspired Mechanical Metamaterials
• Mechanical Cloak via Data-Driven Aperiodic Metamaterial Design
• IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures
• Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties
• FEA-Net: A Physics-guided Data-driven Model for Efficient Mechanical Response Prediction
• A topological encoding method for data-driven photonics inverse design
• Surface Multigrid via Intrinsic Prolongation
• 3D architected isotropic materials with tunable stiffness and buckling strength
• Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
• METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design
• Valley-Hall In-Plane Edge States as Building Blocks for Elastodynamic Logic Circuits
• What machine learning can do for computational solid mechanics
• t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning
• ET-AL: Entropy-Targeted Active Learning for Bias Mitigation in Materials Data
• Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design
• Designing Anisotropic Microstructures with Spectral Density Function
• Remixing Functionally Graded Structures: Data-Driven Topology Optimization with Multiclass Shape Blending

Cited by in corpus (11)

• Experiment-informed finite-strain inverse design of spinodal metamaterials
• Generative Inverse Design of Metamaterials with Functional Responses by Interpretable Learning
• Data driven approaches in nanophotonics: A review of AI-enabled metadevices
• Inverse design of spinodoid structures using Bayesian optimization
• Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces
• Data-driven multifidelity topology design with multi-channel variational auto-encoder for concurrent optimization of multiple design variable fields
• Fixed-Attention Mechanism for Deep-Learning-Assisted Design of High-Degree-of-Freedom 3D Metamaterials
• TorchGDM: A GPU-Accelerated Python Toolkit for Multi-Scale Electromagnetic Scattering with Automatic Differentiation
• Transfer-learned Kolosov-Muskhelishvili Informed Neural Networks for Fracture Mechanics
• Numerical and data-driven modeling of spall failure in polycrystalline ductile materials
• Hetero-EUCLID: Interpretable model discovery for heterogeneous hyperelastic materials using stress-unsupervised learning