Deep Generative Model for Inverse Design of High-Temperature Superconductor Compositions with Predicted T_c > 77 K

Identifying new superconductors with high transition temperatures (T_c > 77 K) is a major goal in modern condensed matter physics. The inverse design of high T_c superconductors relies heavily on an effective representation of the superconductor hyperspace due to the underlying complexity involving many-body physics, doping chemistry and materials, and defect structures. In this study, we propose a deep generative model that combines two widely used machine learning algorithms, namely, the variational auto-encoder (VAE) and the generative adversarial network (GAN), to systematically generate unknown superconductors under the given high T_c condition. After training, we successfully identified the distribution of the representative hyperspace of superconductors with different T_c, in which many superconductor constituent elements were found adjacent to each other with their neighbors in the periodic table. Equipped with the conditional distribution of T_c, our deep generative model predicted hundreds of superconductors with T_c > 77 K, as predicted by the published T_c prediction models in the literature. For the copper-based superconductors, our results reproduced the variation in Tc as a function of the Cu concentration and predicted an optimal T_c = 129.4 K, when the Cu concentration reached 2.41 in Hg_0.37Ba_1.73Ca_1.18Cu_2.41O_6.93Tl_0.69. We expect that such an inverse design model and comprehensive list of potential high Tc superconductors would greatly facilitate future research activities in superconductors.