Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects

Abstract

Data-driven epoch, the development of machine learning (ML) in materials and device design is an irreversible trend. Its ability and efficiency to handle nonlinear and game-playing problems is unmatched by traditional simulation computing software and trial-error experiments. Perovskite solar cells are complex physicochemical devices (systems) that consist of perovskite materials, transport layer materials, and electrodes. Predicting the physicochemical properties and screening the component materials related to perovskite solar cells is the strong point of ML. However, the applications of ML in perovskite solar cells and component materials has only begun to boom in the last two years, so it is necessary to provide a review of the involved ML technologies, the application status, the facing urgent challenges and the development blueprint.

A review on computational modeling of instability and degradation issues of halide perovskite photovoltaic materials

“…In the context of the application of data‐driven models for the study of perovskite‐based optoelectronic devices, broadly, there are the following active areas of research: designing new rules based on large datasets, building predictive models for different properties and building reverse engineering models for materials with targeted properties. There are numerous studies from time to time, summarizing the ebb and flow of application of data‐driven models for the study of perovskites 149–152 . Readers are encouraged to give them a shot in order to develop a comprehensive understanding.…”

“…There are numerous studies from time to time, summarizing the ebb and flow of application of data-driven models for the study of perovskites. [149][150][151][152] Readers are encouraged to give them a shot in order to develop a comprehensive understanding. Keeping up with the spirit of this review, the center of discussion under this section will hover around the stability of halide perovskites.…”

Leveraging machine learning to consolidate the diversity in experimental results of perovskite solar cells

“…7 Machine learning has been extensively used in all the domains of materials science such as superconductors, 8 magnetic materials, 9 crystal system prediction and design, 10 and last but not the least, the materials for solar cells such as organic solar cells 11 and perovskite solar cells. 12 Recent advancements in perovskite solar cells have led to the introduction of ML in PSCs. Simultaneously, there has been a notable increase in publications on the use of machine learning for perovskites, 13 with expanding applications across different avenues.…”

Automatic Screen‐out of Ir(III) Complex Emitters by Combined Machine Learning and Computational Analysis

“…[8][9][10][11] By comprehensively exploring the chemical space with tailored properties, HTVS succeeds in predicting the most promising candidates for experimental validation, and the trial-and-error cost can be remarkably reduced. Recent applications of this approach include the search for both organic and inorganic materials in the field of batteries, [12][13][14][15][16][17] 2D materials, [18][19][20] alloys, [21,22] semiconductors, [23,24] catalyst, [25,26] light-emitting devices, [27,28] and photovoltaics, [29,30] etc. [31][32][33][34] The central part of HTVS is the screening criteria, of which the generation relies on sufficient existing experimental data and/or accurate yet efficient quantum mechanical (QM) calculations.…”