High-performance diffusion model for inverse design of high Tc superconductors with effective doping and accurate stoichiometry

Abstract

The pursuit of designing superconductors with high T_c has been a long-standing endeavor. However, the widespread incorporation of doping in high T_c superconductors significantly impacts electronic structure, intricately influencing T_c. The complex interplay between the structural composition and material performance presents a formidable challenge in superconductor design. Based on a novel generative model, diffusion model, and doping adaptive representation: three-channel matrix, we have designed a high T_c superconductors inverse design model called Supercon-Diffusion. It has achieved remarkable success in accurately generating chemical formulas for doped high T_c superconductors. Supercon-Diffusion is capable of generating superconductors that exhibit high T_c and excels at identifying the optimal doping ratios that yield the peak T_c. The doping effectiveness (55%) and electrical neutrality (55%) of the generated doped superconductors exceed those of traditional GAN models by more than tenfold. Density of state calculations on the structures further confirm the validity of the generated superconductors. Additionally, we have proposed 200 potential high T_c superconductors that have not been documented yet. This groundbreaking contribution effectively reduces the search space for high T_c superconductors. Moreover, it successfully establishes a bridge between the interrelated aspects of composition, structure, and property in superconductors, providing a novel solution for designing other doped materials.