mlsanityData to 14 Oct 2026

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

arXiv 2307.05506 ↗First posted 1 Jul 2023cs.CE cond-mat.mtrl-sci cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 62 of its 325 references that are in the map. First posted on arXiv 1 Jul 2023.

Builds on

62 of 325 references.

References · 62

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  4. 2014Conditional Generative Adversarial Netscited by 2,162
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  6. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  7. 2017Deep Bayesian Active Learning with Image Datacited by 819
  8. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  9. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 608
  10. 2020A Survey of Deep Active Learningcited by 554
  11. 2013Gaussian Processes for Big Datacited by 383
  12. 2020A Brief Review of Domain Adaptationcited by 288
38 more
  1. 2021Physics-informed neural networks with hard constraints for inverse designcited by 280
  2. 2018When Gaussian Process Meets Big Data: A Review of Scalable GPscited by 206
  3. 2019Exact Gaussian Processes on a Million Data Pointscited by 119
  4. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  5. 2021Deep Generative Models in Engineering Design: A Reviewcited by 105
  6. 2020Generalized and Scalable Optimal Sparse Decision Treescited by 100
  7. 2021A physics-informed variational DeepONet for predicting the crack path in brittle materialscited by 98
  8. 2022DataPerf: Benchmarks for Data-Centric AI Developmentcited by 90
  9. 2020GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactionscited by 82
  10. 2022Reliable extrapolation of deep neural operators informed by physics or sparse observationscited by 62
  11. 2020Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systemscited by 52
  12. 2022On the use of Artificial Neural Networks in Topology Optimisationcited by 36
  13. 2020Airfoil Design Parameterization and Optimization using B'ezier Generative Adversarial Networkscited by 35
  14. 2019Global optimization of dielectric metasurfaces using a physics-driven neural networkcited by 30
  15. 2021A Data-Centric Approach for Training Deep Neural Networks with Less Datacited by 28
  16. 2023Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material propertiescited by 24
  17. 2020Data-driven topology optimization of spinodoid metamaterials with seamlessly tunable anisotropycited by 23
  18. 2021IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structurescited by 19
  19. 2021Data-Driven Design-by-Analogy: State of the Art and Future Directionscited by 18
  20. 2019Designing nanophotonic structures using conditional-deep convolutional generative adversarial networkscited by 16
  21. 2020Data-Driven Topology Optimization with Multiclass Microstructures using Latent Variable Gaussian Processcited by 16
  22. 2020METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Designcited by 15
  23. 2019Multifunctional Metasurface Design with a Generative Adversarial Networkcited by 14
  24. 2018Freeform Diffractive Metagrating Design Based on Generative Adversarial Networkscited by 13
  25. 2020FEA-Net: A Physics-guided Data-driven Model for Efficient Mechanical Response Predictioncited by 13
  26. 2021What machine learning can do for computational solid mechanicscited by 12
  27. 2021Scalable Gaussian Processes for Data-Driven Design using Big Data with Categorical Factorscited by 11
  28. 2017Two-Scale Topology Optimization with Microstructurescited by 10
  29. 2018Scalable Gaussian Processes with Grid-Structured Eigenfunctions (GP-GRIEF)cited by 9
  30. 2021Data-Driven Multiscale Design of Cellular Composites with Multiclass Microstructures for Natural Frequency Maximizationcited by 9
  31. 2022GAN-DUF: Hierarchical Deep Generative Models for Design Under Free-Form Geometric Uncertaintycited by 9
  32. 2022t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learningcited by 9
  33. 2021De-homogenization using Convolutional Neural Networkscited by 7
  34. 2014Topology optimization based on moving deformable components: A new computational frameworkcited by 6
  35. 2021Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexitycited by 6
  36. 2021Mechanical Cloak via Data-Driven Aperiodic Metamaterial Designcited by 6
  37. 2022MetaNOR: A Meta-Learnt Nonlocal Operator Regression Approach for Metamaterial Modelingcited by 6
  38. 2022Uncertainty-Aware Mixed-Variable Machine Learning for Materials Designcited by 6

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 8; 2026: 3.

17 papers.

Sort:

By area:

  1. 2024AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligencecited by 36
  2. 2024Guided Diffusion for Fast Inverse Design of Density-based Mechanical Metamaterialscited by 7
  3. 2025MIND: Microstructure INverse Design with Generative Hybrid Neural Representationcited by 4
  4. 2025Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfacescited by 4
  5. 2023Generative Inverse Design of Metamaterials with Functional Responses by Interpretable Learningcited by 3
  6. 2025MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generationcited by 3
  7. 2024Two-Stage Surrogate Modeling for Data-Driven Design Optimization with Application to Composite Microstructure Generationcited by 2
  8. 2024FFT-based surrogate modeling of auxetic metamaterials with real-time prediction of effective elastic properties and swift inverse designcited by 2
  9. 2025ReBaNO: Reduced Basis Neural Operator Mitigating Generalization Gaps and Achieving Discretization Invariancecited by 2
  10. 2025Data driven approaches in nanophotonics: A review of AI-enabled metadevicescited by 2
  11. 2025Reduced-order structure-property linkages for stochastic metamaterialscited by 1
  12. 2025Diffusion-Based Electromagnetic Inverse Design of Scattering Structured Mediacited by 1
5 more
  1. 2024Machine Learning-Guided Design of Non-Reciprocal and Asymmetric Elastic Chiral Metamaterialscited by 0
  2. 2025Heterogeneous Metamaterials Design via Multiscale Neural Implicit Representationcited by 0
  3. 2026RAG: A Random-Forest-Based Generative Design Framework for Uncertainty-Aware Design of Metamaterials with Complex Functional Response Requirementscited by 0
  4. 2026One-Shot Generative Design for Disordered Metamaterials via Self-Organizing Neural Cellular Automatacited by 0
  5. 2026Diffusion-Based Inverse Design of Dielectric Resonator Metasurfaces for Shaping Smart Electromagnetic Environmentscited by 0