Predicting Quasiparticle and Excitonic properties of materials using Machine Learning
ORAL
Abstract
In the recent years, GW-BSE has been proven to be extremely successful in studying the quasiparticle bandstructures and excitonic effects in the optical properties of materials. However, the massive computational cost associated with such calculations restricts their applicability in high-throughput material discovery studies aimed to unearth future generations of promising photocatalysts, photovoltaics, and many more diverse photoabsorption-related applications. Here, we have completed GW-BSE calculation of ~1000 materials using a high-throughput workflow implemented in our pyGWBSE python-package. These materials were selected from the Materials Project database and have up to 4 atoms per unit cell. Multiple supervised machine learning methods were then employed on this dataset to investigate the applicability of the methods in predicting the quasiparticle and excitonic properties of the ~1000 materials. We also explore the viability of using DFT computed properties as a training dataset together with transfer learning methods to overcome the problem of the unavailability of a larger GW-BSE dataset.
*This work was supported by the Arizona State University start-up funds and in part as part of ULTRA, an Energy Frontier Research Center funded by the U.S. Department of Energy (DOE), Office of Science, Basic Energy Sciences (BES), under Award # DE-SC0021230 (GW-BSE high-throughput simulations). In addition, Singh acknowledges support by the NSF DMR-grant NSF-DMR #1906030. The authors acknowledge the San Diego Supercomputer Center under the NSF-XSEDE Award No. DMR150006 and the Research Computing at Arizona State University for providing HPC resources. This research used resources of the National Energy Research Scientific Computing Center, a DOE Office of Science User Facility supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231.
