Machine Learning Augmented Discovery of Chalcogenide Double Perovskites for Photovoltaics. Issue 5 (18th March 2019)

• Record Type: Journal Article
• Authors: L. Agiorgousis, Michael; Sun, Yi‐Yang; Choe, Duk‐Hyun; West, Damien; Zhang, Shengbai
• Is Part Of: Advanced theory and simulations. Volume 2:Issue 5(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-03-18
• Subjects: density functional theory -- machine learning -- perovskites -- photovoltaics; Science -- Simulation methods -- Periodicals; Science -- Methodology -- Periodicals; Engineering -- Simulation methods -- Periodicals; Engineering -- Methodology -- Periodicals; 507.21
• DOI: 10.1002/adts.201800173
• Languages: English
• ISSNs: 2513-0390

Abstract

Abstract: Hybrid organic inorganic perovskite solar cells based on CH3 NH3 PbI3 have drastically increased in efficiency over the past several years and are competitive with decades‐old photovoltaic materials such as CdTe. Despite this impressive increase, significant issues still remain due to the intrinsic instability of CH3 NH3 PbI3 which degrades into carcinogenic PbI2 . Recently, double halide perovskites which use a pair of 1 + –3 + cations to replace Pb 2+, such as Cs2 InSbI6, and chalcogenide perovskites, such as BaZrS3, have been explored as potential replacements. In this work, double chalcogenide perovskites are explored to identify novel photovoltaic absorbers that can replace CH3 NH3 PbI3 . Due to the large space of possible compounds, machine learning methods are used to classify materials as potential photovoltaic absorbers using data from the periodic table, eliminating wasteful computation. A random forest algorithm achieves a cross‐validation accuracy of 86.4% on the constructed data set. Over 450 possible replacements are identified via traditional and statistical methods with Ba2 AlNbS6, Ba2 GaNbS6, Ca2 GaNbS6, Sr2 InNbS6, and Ba2 SnHfS6 as the most promising alternative when thermodynamic stability, kinetic stability, and optical absorption are considered. Abstract : A combination of high‐throughput calculations and machine learning are used to screen double chalcogenide perovskites for photovoltaic application. A random forest algorithm is used to classify materials as photovoltaic absorbers using data taken from the periodic table. Promising materials are screened for optical absorption, effective masses, thermal stability, and kinetic stability. Several materials show super‐high absorption relative to thin‐film CdTe.