Abstract: Semiconductors with desirable electronic band structure and optical absorption are sought for solar cells, electronic devices, infrared sensors and quantum computing. Compositional manipulation via alloying at cation or anion sites, or via incorporation of point defects and impurities, can help tune the properties of semiconductors in known chemical spaces.

In this work, we develop AI-based frameworks for the on-demand prediction of the phase stability, band gap, optical absorption spectra, photovoltaic figures of merit, defect formation energies, and impurity energy levels in two broad classes of semiconductors, namely (a) halide perovskites with the general formula ABX3 (where A is a large organic or inorganic monovalent cation, B is a divalent cation and X is a halogen anion), and (b) group IV, III-V and II-VI semiconductors in the zinc blende structure. These frameworks are powered by high-throughput density functional theory (DFT) computations, unique encoding of the atom-composition-structure information, and rigorous training of advanced neural network-based predictive and optimization models. Multi-fidelity learning is applied to bridge the gap between (high quantities of) low accuracy calculations and (lower quantities of) high-fidelity data, constituted of data from advanced DFT functionals. AI-based recommendations are synergistically coupled with targeted synthesis and characterization, leading to successful validation and discovery of novel compositions for improved performance in solar cells.

Bio: Arun Mannodi Kanakkithodi is an assistant professor in Materials Engineering at Purdue University. He received his PhD in Materials Science and Engineering from the University of Connecticut in 2017 and worked as a postdoctoral researcher at the Center for Nanoscale Materials in Argonne National Laboratory from 2017 to 2020.