Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning Strategy

By Wei Ma, Feng Cheng, Yihao Xu, Qinlong Wen, Yongmin Liu. 2019

534 citations recorded by the source corpus.

The research of metamaterials has achieved enormous success in the manipulation of light in a prescribed manner using delicately designed subwavelength structures, so‐called meta‐atoms. Even though modern numerical methods allow for the accurate calculation of the optical response of complex structures, the inverse design of metamaterials, which aims to retrieve the optimal structure according to given requirements, is still a challenging task owing to the nonintuitive and nonunique relationship between physical structures and optical responses. To better unveil this implicit relationship and thus facilitate metamaterial designs, it is proposed to represent metamaterials and model the inverse design problem in a probabilistically generative manner, enabling to elegantly investigate the complex structure–performance relationship in an interpretable way, and solve the one‐to‐many mapping issue that is intractable in a deterministic model. Moreover, to alleviate the burden of numerical calculations when collecting data, a semisupervised learning strategy is developed that allows the model to utilize unlabeled data in addition to labeled data in an end‐to‐end training. On a data‐driven basis, the proposed deep generative model can serve as a comprehensive and efficient tool that accelerates the design, characterization, and even new discovery in the research domain of metamaterials, and photonics in general.

Subfields: Atomic and Molecular Physics, and Optics, Developmental Biology, Electronic, Optical and Magnetic Materials

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Developmental Biology

Cynthia Rudin

In Electronic, Optical and Magnetic Materials

Citations in the corpus

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “In meta-material design [121], design pattern and optical responses are encoded into latent variables to be characterized by Variational Auto Encoder (VAE).”
How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning (2021, background): “12 [14] Wei Ma, Feng Cheng, Yihao Xu, Qinlong Wen, Yongmin Liu, Probabilistic representation and inverse design of metamaterials based on a deep generative model with semi-supervised learning strategy, Adv.”
Deep Generative Models in Engineering Design: A Review (2021, background): “[92] propose a novel VAE-based framework consisting of feature extraction, prediction, recognition, and generation networks.”
Deep learning for the design of photonic structures (2020, methodology): “By combining traditional optimization techniques and a generative model, global optimization of a 1D meta-grating can be achieved with high efficiency for various wavelengths and deflection angles 76 .”
Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems (2020, methodology): “In the area of material design, deep generative models had been applied to the microstructure characterization and reconstruction of nanomaterials and alloys [37, 38], design of material microstructure morphologies [39], heat conduction materials [40], and design of photonic/phononic metamaterials [”
Interfacing photonics with artificial intelligence: an innovative design strategy for photonic structures and devices based on artificial neural networks (2021, methodology): “The desired designs and structures are oftentimes hard to parameterize, especially when the structure of interest contains many basic shapes [41,65] or is freeform [66,67].”