Fast inverse design of microstructures via generative invariance networks

Xian Yeow Lee, Joshua R. Waite, Chih Hsuan Yang, Balaji Sesha Sarath Pokuri, Ameya Joshi, Aditya Balu, Chinmay Hegde, Baskar Ganapathysubramanian, Soumik Sarkar

    Research output: Contribution to journalArticlepeer-review


    The problem of the efficient design of material microstructures exhibiting desired properties spans a variety of engineering and science applications. The ability to rapidly generate microstructures that exhibit user-specified property distributions can transform the iterative process of traditional microstructure-sensitive design. We reformulate the microstructure design process using a constrained generative adversarial network (GAN) model. This approach explicitly encodes invariance constraints within GANs to generate two-phase morphologies for photovoltaic applications obeying design specifications: specifically, user-defined short-circuit current density and fill factor combinations. Such invariance constraints can be represented by differentiable, deep learning-based surrogates of full physics models mapping microstructures to photovoltaic properties. Furthermore, we propose a multi-fidelity surrogate that reduces expensive label requirements by a factor of five. Our framework enables the incorporation of expensive or non-differentiable constraints for the fast generation of microstructures (in 190 ms) with user-defined properties. Such proposed physics-aware data-driven methods for inverse design problems can be used to considerably accelerate the field of microstructure-sensitive design.

    Original languageEnglish (US)
    Pages (from-to)229-238
    Number of pages10
    JournalNature Computational Science
    Issue number3
    StatePublished - Mar 2021

    ASJC Scopus subject areas

    • Computer Science (miscellaneous)
    • Computer Science Applications
    • Computer Networks and Communications


    Dive into the research topics of 'Fast inverse design of microstructures via generative invariance networks'. Together they form a unique fingerprint.

    Cite this