Using Deep Machine Learning to Understand the Physical Performance Bottlenecks in Novel Thin‐Film Solar Cells

Majeed, Nahdia; Saladina, Maria; Krompiec, Michal; Greedy, Steve; Deibel, Carsten; Mackenzie, Roderick C I

Abstract

There is currently a worldwide effort to develop novel materials for solar energy harvesting which are efficient, low cost and do not emit significant levels of CO 2 during manufacture. Currently when a researcher fabricates a novel device from a novel material system, it often takes many weeks of experimental effort and data analysis to understand why any given device/material combination produces an efficient or poorly optimized cell. The net result of this is that it can often take the community tens of years to transform a promising material system (e.g. perovskites/small molecule devices) to a fully optimized cell ready for production. In this work, we develop a new and rapid approach to understanding device/material performance which uses a combination of machine learning, device modeling and experiment. The method is able to provide a set of electrical device parameters (charge carrier mobilities, recombination rates etc..) in a matter of seconds, rather than days and thus offers a fast way to directly link fabrication conditions to device/material performance, pointing a way to further and more rapid optimization of light harvesting devices. We demonstrate the method by using it to understand annealing temperature and surfactant choice and in terms of charge transport and recombination constants for organic solar cells made from the P3HT:PCBM, PBTZT-stat-BDTT-8:PCBM and PTB7:PCBM material systems.

Citation

Majeed, N., Saladina, M., Krompiec, M., Greedy, S., Deibel, C., & Mackenzie, R. C. I. (2020). Using Deep Machine Learning to Understand the Physical Performance Bottlenecks in Novel Thin‐Film Solar Cells. Advanced Functional Materials, 30(7), Article 1907259. https://doi.org/10.1002/adfm.201907259

• Journal Article Type: Article
• Acceptance Date: Nov 15, 2019
• Online Publication Date: Dec 15, 2019
• Publication Date: Feb 12, 2020
• Deposit Date: Dec 5, 2019
• Publicly Available Date: Dec 16, 2020
• Journal: Advanced Functional Materials
• Print ISSN: 1616-301X
• Electronic ISSN: 1616-3028
• Publisher: Wiley
• Peer Reviewed: Peer Reviewed
• Volume: 30
• Issue: 7
• Article Number: 1907259
• DOI: https://doi.org/10.1002/adfm.201907259
• Public URL: https://nottingham-repository.worktribe.com/output/3486733
• Publisher URL: https://onlinelibrary.wiley.com/doi/full/10.1002/adfm.201907259
• Additional Information: This is the peer reviewed version of the following article: Majeed, N., Saladina, M., Krompiec, M., Greedy, S., Deibel, C., MacKenzie, R. C. I., Using Deep Machine Learning to Understand the Physical Performance Bottlenecks in Novel Thin‐Film Solar Cells. Adv. Funct. Mater. 2019, 1907259, which has been published in final form at https://doi.org/10.1002/adfm.201907259. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions