Deep learning modeling strategy for material science: from natural materials to metamaterials

Abstract

Computational modeling is a crucial approach in material-related research for discovering new materials with superior properties. However, the high design flexibility in materials, especially in the realm of metamaterials where the sub-wavelength structure provides an additional degree of freedom in design, poses a formidable computational cost in various real-world applications. With the advent of big data, deep learning brings revolutionary breakthroughs in many conventional machine learning and pattern recognition tasks such as image classification. The accompanied data-driven modeling paradigm also provides transformative methodology shift in materials science, from trial-and-error routine to intelligent material discovery and analysis. This review systematically summarize the application of deep learning in material science, based on a model selection perspective for both natural materials and metamaterials. The review aims to uncover the logic behind data-model relation with emphasis on suitable data structures for different scenarios in the material study and the corresponding problem-solving deep learning model architectures.

Neural network modeling and prediction of HfO 2 thin film properties tuned by thermal annealing

“…Back-propagation neural networks (BPNNs), a subset of machine learning, have shown potential for mapping the relationship between experimental parameters and material properties [ 13 , 14 ] . This approach can identify underlying regularities in the training data by updating the internal weight parameters [ 15 , 16 ] .…”

Deep‐Learning‐Enabled Intelligent Design of Thermal Metamaterials

“…Metamaterials are typical heterogeneous hybrid materials with promising capabilities on field manipulation resulting from the combination of structure and composition. [1][2][3] As a thermal diffusion counterpart, thermal metamaterials DOI: 10.1002/adma.202302387 including cloak, [3][4][5][6][7][8][9] concentrator, [10][11][12][13][14] rotator, [15,16] transparency, [17] and illusion, [18,19] have been designed by transformation thermotics. [3] and scattering cancellation methods.…”

Physics‐Informed Machine Learning for Inverse Design of Optical Metamaterials

“…In this study, it is seen that the tandem model slightly outperforms the generative models in terms of target reconstruction for low degree of freedom structure. Since tandem networks have a relatively simple architecture, they are able to capture the response-design relationship with less data requirement [17,34] and easier hyper-parameter tuning [35] than the generative models.…”