Machine Learning Enables Prediction of Halide Perovskites’ Optical Behavior with >90% Accuracy
ACS Energy Letters · 14.04.2023 · 8 (4) · 1716-1722
DOI: 10.1021/acsenergylett.2c02555 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACS Energy Letters, online erschienen am 10.03.2023. Verfasst von Meghna Srivastava und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Materials Science and Engineering, UC Davis, Davis, California 95616, United States. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Division of Electrical, Communications and Cyber Systems, Sandia National Laboratories.
Abstract (Originalsprache)
The composition-dependent degradation of hybrid organic-inorganic perovskites (HOIPs) due to environmental stressors still precludes their commercialization. It is very difficult to quantify their behavior upon exposure to each stressor by exclusively using trial-and-error methods due to the high-dimensional parameter space involved. We implement machine learning (ML) models using high-throughput, in situ photoluminescence (PL) to predict the response of Cs y FA1-y Pb(Br x I1-x )3 while exposed to relative humidity cycles. We quantitatively compare three ML models while generating forecasts of environment-dependent PL responses: linear regression, echo state network, and seasonal autoregressive integrated moving average with exogenous regressor algorithms. We achieve accuracy of >90% for the latter, while tracking PL changes over a 50 h window. Samples with 17% of Cs content consistently showed a PL increase as a function of cycle. Our precise time-series forecasts can be extended to other HOIP families, illustrating the potential of data-centric approaches to accelerate material development for clean-energy devices.
Autor:innen und Institutionen
- Department of Materials Science and Engineering, UC Davis, Davis, California 95616, United States.
- Department of Materials Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States.
ORCID-Profile: Meghna Srivastava, Abigail R Hering, Yu An, Juan-Pablo Correa-Baena, Marina S Leite
Förderung
- Division of Electrical, Communications and Cyber Systems
- Sandia National Laboratories
Zitieren
APA
Srivastava, M., Hering, A. R., An, Y., Correa-Baena, J. P., & Leite, M. S. (2023). Machine Learning Enables Prediction of Halide Perovskites’ Optical Behavior with >90% Accuracy. ACS Energy Letters, 8(4), 1716-1722. https://doi.org/10.1021/acsenergylett.2c02555
Vancouver
Srivastava M, Hering AR, An Y, Correa-Baena JP, Leite MS. Machine Learning Enables Prediction of Halide Perovskites’ Optical Behavior with >90% Accuracy. ACS Energy Letters. 2023;8(4):1716-1722. doi:10.1021/acsenergylett.2c02555
BibTeX
@article{Srivastava2023,
author = {Srivastava, Meghna and Hering, Abigail R and An, Yu and Correa-Baena, Juan-Pablo and Leite, Marina S},
title = {Machine Learning Enables Prediction of Halide Perovskites’ Optical Behavior with >90% Accuracy},
journal = {ACS Energy Letters},
year = {2023},
volume = {8},
number = {4},
pages = {1716--1722},
doi = {10.1021/acsenergylett.2c02555}
}
EUVIMED