2020/05/31 by Zekun Ren, Siyu Isaac Parker Tian, Juhwan Noh +14 · 1 citation
Physics and Astronomy · Computer Science · #physics.comp-ph #cond-mat.mtrl-sci #cs.LG
paper · pdf · doi:10.1016/j.matt.2021.11.032
arxiv created 2021/12/15 · arxiv updated 2022/01/19
Realizing general inverse design could greatly accelerate the discovery of new materials with user-defined properties. However, state-of-the-art generative models tend to be limited to a specific composition or crystal structure. Herein, we present a framework capable of general inverse design (not limited to a given set of elements or crystal structures), featuring a generalized invertible representation that encodes crystals in both real and reciprocal space, and a property-structured latent space from a variational autoencoder (VAE). In three design cases, the framework generates 142 new crystals with user-defined formation energies, bandgap, thermoelectric (TE) power factor, and combinations thereof. These generated crystals, absent in the training database, are validated by first-principles calculations. The success rates (number of first-principles-validated target-satisfying crystals/number of designed crystals) ranges between 7.1% and 38.9%. These results represent a significant step toward property-driven general inverse design using generative models, although practical challenges remain when coupled with experimental synthesis.