An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties

• Main Authors: Ren, Zekun, Tian, Isaac Parker Siyu, Noh, Juhwan, Oviedo, Felipe, Xing, Guangzong, Li, Jiali, Liang, Qiaohao, Zhu, Ruiming, Aberle, Armin G., Sun, Shijing, Wang, Xiaonan, Liu, Yi, Li, Qianxiao, Jayavelu, Senthilnath, Hippalgaonkar, Kedar, Jung, Yousung, Buonassisi, Tonio
• Other Authors: School of Materials Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Materials; Auto Encoders; General Inverse Design
• Online Access: https://hdl.handle.net/10356/164192
• Institution: Nanyang Technological University

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.