Comparing Hyper-optimized Machine Learning Models for Predicting Efficiency Degradation in Organic Solar Cells

2024-03-29

arXiv.org

AI Summary

This study addresses the temporal degradation prediction of power conversion efficiency (PCE) in multilayer organic solar cells (ITO/PEDOT:PSS/P3HT:PCBM/Al) over 180 days. We construct a dataset comprising 996 samples, each characterized by seven process- and environment-related variables. We propose a novel automated machine learning framework that systematically explores hyperparameters and random seeds via Bayesian optimization, multi-model benchmarking, and a reproducible command-line interface pipeline. Our approach achieves high-accuracy generalization to unseen devices (R² = 0.96–0.97, RMSE ≈ 1% PCE), markedly outperforming conventional nonlinear least-squares Bayesian regression. Furthermore, it quantifies the relative influence of key input variables, enabling data-driven stability optimization. All data, code, and standardized reporting artifacts are publicly released to ensure full reproducibility.

Technology Category

• Machine Learning: Auto ML and Hyperparameter Tuning
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This work presents a set of optimal machine learning (ML) models to represent the temporal degradation suffered by the power conversion efficiency (PCE) of polymeric organic solar cells (OSCs) with a multilayer structure ITO/PEDOT:PSS/P3HT:PCBM/Al. To that aim, we generated a database with 996 entries, which includes up to 7 variables regarding both the manufacturing process and environmental conditions for more than 180 days. Then, we relied on a software framework that brings together a conglomeration of automated ML protocols that execute sequentially against our database by simply command-line interface. This easily permits hyper-optimizing and randomizing seeds of the ML models through exhaustive benchmarking so that optimal models are obtained. The accuracy achieved reaches values of the coefficient determination (R2) widely exceeding 0.90, whereas the root mean squared error (RMSE), sum of squared error (SSE), and mean absolute error (MAE)>1% of the target value, the PCE. Additionally, we contribute with validated models able to screen the behavior of OSCs never seen in the database. In that case, R2~0.96-0.97 and RMSE~1%, thus confirming the reliability of the proposal to predict. For comparative purposes, classical Bayesian regression fitting based on non-linear mean squares (LMS) are also presented, which only perform sufficiently for univariate cases of single OSCs. Hence they fail to outperform the breadth of the capabilities shown by the ML models. Finally, thanks to the standardized results offered by the ML framework, we study the dependencies between the variables of the dataset and their implications for the optimal performance and stability of the OSCs. Reproducibility is ensured by a standardized report altogether with the dataset, which are publicly available at Github.

Problem

• Predicting efficiency degradation in organic solar cells using ML models
• Optimizing ML models for accuracy in PCE degradation prediction
• Comparing ML models with classical Bayesian regression methods

Innovation

• Hyper-optimized ML models for OSC degradation prediction
• Automated ML framework with exhaustive benchmarking
• Validated models for unseen OSC behavior screening