Challenges, Opportunities, and Prospects in Metal Halide Perovskites from Theoretical and Machine Learning Perspectives

Abstract

Metal halide perovskite (MHP) is a promising next generation energy material for various applications, such as solar cells, light emitting diodes, lasers, sensors, and transistors. MHPs show excellent mechanical, dielectric, photovoltaic, photoluminescence, and electronic properties, and such intriguing physical and chemical properties have drawn attention recently. However, there exists a chasm between the successful applications of MHPs and theoretical understandings. The difficulty arises from the intrinsic properties of MHPs, including structural disorder, ionic interactions, nonadiabatic effects, and composition diversity. Machine learning (ML) approaches have shown great promise as a tool to overcome the theoretical obstacles in many fields of science. In this perspective, the pending theoretical challenges from experiments are overviewed and promising ML approaches, including ab initio ML potentials, materials design/optimization models, and data mining strategies are proposed. Possible roles and pipelines of ML frameworks are highlighted to close the gap between experiment and theory in MHPs.

The challenge of studying perovskite solar cells’ stability with machine learning

“…The abundance of data allows the application of statistical techniques, most notably machine learning (ML), to empower data-driven research activities and for gaining new insights that would be otherwise impossible to obtain by analyzing data from individual studies only. Several authors have already pointed at ML as one important tool in overcoming challenges (Myung et al, 2022) in perovskite research, for example, screening of suitable candidate materials for photovoltaic applications (Chen et al, 2022), or to use data extracted from scientific publications to characterize the performance of PSCs (Liu et al, 2022). Thus far, few authors have attempted to use shared data to examine the stability of perovskite solar cells (Beyza Yılmaz and Ramazan Yıldırım, 2021).…”

High-Throughput Screening on Halide Perovskite Derivatives and Rational Design of Cs3LuCl6

“…20,21 In addition, understanding low-dimensional inorganic metal halides' physical and chemical nature still remains a mystery. 22 The challenges of gaining insights into the design and synthesis of inorganic metal halides have largely contributed to the lack of known materials in this class. These knowledge constraints also present significant risks to the exploratory synthesis of overall inorganic metal halide materials.…”

Rotor Lattice Model of Ferroelectric Large Polarons

“…It turned out, however, that HOIP are also notoriously complex in terms of their physical properties, inter alia due to their soft structure [10], ionic mobility [11,12], and the interplay between cation rotational dynamics and structural, (photo)electric and stability properties of HOIP [13][14][15][16]. Recently a lot of progress has been made in theoretical understanding of HOIP using density functional theory [17][18][19][20], molecular dynamics [21] and machine learning [22][23][24] approaches. Based on atomistic simulations it is, however, challenging to achieve a simple intuitive understanding independent of the microscopic details, which motivates us to look for a simple model capturing the key physical properties of HOIP.…”