Researchers use machine learning to accelerate computational study of perovskite alloy materials
Researchers from the CEST team have published a study demonstrating the effectiveness of machine learning methods to identify suitable perovskite solar cell materials. Perovskite solar cells are a new technology attracting a lot of interest due to their high efficiency and potential for radical cost reduction when compared to traditional silicon-based solar cells.
Despite its promising qualities, commercialization perovskite solar battery were restrained by their rapid degradation under environmental stress, such as temperature and humidity. They also contain toxic substances which can have a negative impact on the environment. The search for new perovskite materials without these problems is ongoing, but established computational and experimental research methods cannot handle the large number of material candidates that need to be tried and tested. test.
CEST members Jarno Laakso and Patrick Rinke, with collaborators from the University of Turku and China, developed a new machine learning-based method for rapid prediction of perovskite properties. This new method speeds up calculations and can be used to study perovskite alloys. These alloy materials contain many candidates for improved solar cell materials, but studying them is difficult with conventional computational methods.
The researchers demonstrated the effectiveness of the new method by finding the most stable mixing fractions for the CsPbCl alloy.3 and CsPbBr3 perovskite. Having an effective method to study the stability of perovskite alloys is an important step towards engineering solar cells that are more resilient to degradation.
The same method that was applied to perovskite in this study could advance the discovery of other new alloy materials. After initial success with their machine learning approach, Laakso and collaborators are looking at studying more complex perovskite alloys to discover highly efficient, nontoxic, and capable solar cell materials. anti-degradation.
The study was published in the journal Physics study material.
Jarno Laakso et al, Synthetic engineering of perovskites with machine learning, Physics study material (2022). DOI: 10.1103/PhysRevMaterials.6.113801
Provided by
Aalto University
quote: Researchers using machine learning to accelerate computational study of perovskite alloy materials (2022, November 30) retrieved November 30, 2022 from https://techxplore.com/news/2022 -11-machine-perovskite-alloy-materials.html
This document is the subject for the collection of authors. Other than any fair dealing for private learning or research purposes, no part may be reproduced without written permission. The content provided is for informational purposes only.