article · Materials for Renewable and Sustainable Energy
Machine learning algorithms can assist in solving engineering challenges related to solar energy performance. This work analyses the application of four regression models: random forest, gradient boosting, K-nearest neighbours, and linear regression, alongside hyperparameter tuning techniques. These models were tested across three perovskite solar cell datasets of varying size and complexity to predict power conversion efficiency. The evaluation monitored model accuracy, complexity, computational cost, and processing time to provide guidance for data-driven solar projects. Furthermore, an assessment of feature importance across the datasets revealed that electron transport layer doping is the dominant variable controlling overall power conversion efficiency. Doping in this layer accounted for 93.6 percent of the contribution to efficiency in the first dataset and 79.0 percent in the third dataset.
Improving solar cell efficiency often demands navigating complex material datasets. Demonstrating how standard machine learning models balance computational cost against accuracy helps researchers select appropriate computational tools. Pinpointing electron transport layer doping as the dominant contributor to power conversion efficiency also highlights where experimentalists should concentrate their efforts to achieve higher performance.
This work provides model selection guidance for computational researchers and solar cell developers using data-driven methods to optimise device efficiency. By highlighting electron transport layer doping as the most influential parameter, it informs experimental design priorities. The findings represent early-stage analytical research rather than a validated software product or near-market manufacturing solution.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Utilizing artificial intelligent based algorithms in solving engineering problems is widely spread nowadays. Herein, this study provides a comprehensive and insightful analysis of the application of machine learning (ML) models to complex datasets in the field of solar cell power conversion efficiency (PCE). Mainly, perovskite solar cells generate three datasets, varying dataset size and complexity. Various popular regression models and hyperparameter tuning techniques are studied to guide researchers and practitioners looking to leverage machine learning methods for their data-driven projects. Specifically, four ML models were investigated; random forest (RF), gradient boosting (GBR), K-nearest neighbors (KNN), and linear regression (LR), while monitoring the ML model accuracy, complexity, computational cost, and time as evaluating parameters. Inputs' importance and contribution were examined for the three datasets, recording a dominating effect for the electron transport layer's (ETL) doping as the main controlling parameter in tuning the cell's overall PCE. For the first dataset, ETL doping recorded 93.6%, as the main contributor to the cell PCE, reducing to 79.0% in the third dataset.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s40243-023-00239-2
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
