Generative design of stable semiconductor materials using deep learning and density functional theory

Abstract

Semiconductor device technology has greatly developed in complexity since discovering the bipolar transistor. In this work, we developed a computational pipeline to discover stable semiconductors by combining generative adversarial networks (GAN), classifiers, and high-throughput first-principles calculations. We used CubicGAN, a GAN-based algorithm for generating cubic materials and developed a classifier to screen the semiconductors and studied their stability using first principles. We found 12 stable AA{}^{prime}MH6 semiconductors in the F-43m space group including BaNaRhH6, BaSrZnH6, BaCsAlH6, SrTlIrH6, KNaNiH6, NaYRuH6, CsKSiH6, CaScMnH6, YZnMnH6, NaZrMnH6, AgZrMnH6, and ScZnMnH6. Previous research reported that five AA{}^{prime}IrH6 semiconductors with the same space group were synthesized. Our research shows that AA{}^{prime}MnH6 and NaYRuH6 semiconductors have considerably different properties compared to the rest of the AA{}^{prime}MH6 semiconductors. Based on the accurate hybrid functional calculations, AA{}^{prime}MH6 semiconductors are found to be wide-bandgap semiconductors. Moreover, BaSrZnH6 and KNaNiH6 are direct-bandgap semiconductors, whereas others exhibit indirect bandgaps.