Simultaneous Optimization of Donor/Acceptor Pairs and Device Specifications for Nonfullerene Organic Solar Cells Using a QSPR Model with Morphological Descriptors

Abstract

In addition to designing new donor (D) and/or acceptor (A) molecules, the optimization of experimental fabrication conditions for the organic solar cells (OSCs) is also a complex, multidimensional challenge, which hasn't been theoretically explored. Herein, a new framework for simultaneous optimizing D/A molecule pairs and device specifications of OSCs is proposed, through a quantitative structureproperty relationships (QSPR) model built by machine learning. Combining the device parameters with structural and electronic variables, the built QSPR model achieved unprecedentedly high accuracy and consistency. Additionally, a huge chemical space containing 1,942,785 D/A pairs is explored to find potential synergistic ones. Favorable expereimental parameters such as root-mean-square (RMS) and the D/A ratio (DAratio) are further screened by grid search methods. Overall, this study suggests the feasibility to optimize D/A molecule pairs and device specifications simultaneously by enabling better-informed and data-driven techniques and this could facilitate the acceleration of improving OSCs efficiencies.

Performance Prediction and Experimental Optimization Assisted by Machine Learning for Organic Photovoltaics

“…[ 25 ] In contrast to the widely used FAs, the optical properties and electronic energy levels of NFAs can be easily tuned, [ 26 ] leading to a rapid increase in PCEs for NFA‐based OSCs, with values now exceeding 19%. [ 3 ] Since 2019, a few NFA‐based OPV datasets with data points around 100–600 have been built by several groups [13a,14a,b,27] . Furthermore, Lee et al [27c] and Hao et al [27d] collected 135 and 157 experimental data points to construct ternary NFA‐OPV datasets respectively.…”

“…A variety of ML methodologies have been applied for OPV. They have been presented in greater detail in numerous reviews [4c,12,13b,40] and textbooks, and [ 41 ] therefore their mathematical details are not repeated in this work. A group of methodologies including support vector regression (SVR), [ 42 ] support vector machine (SVM), [ 43 ] and kernel ridge regression (KRR) [ 44 ] can be described as an enhancement of conventional linear regression (LR) [ 45 ] methods to include nonlinear dependency of the descriptors and observables.…”

“…The RF and boosted regression trees (BRT) showed better prediction accuracy with r at 0.70 and 0.71 and RMSE at 1.17 and 2.42, respectively. Recently, Wen et al [13a] constructed QSPR models with molecular descriptors and parameters related to morphology (D:A weight ratio and RMS roughness of atomic force microscope images) for NFA‐based OPVs with more polymers chosen as donors. As shown in Figure , the constructed ML voting model (linear combination of the predictions from several regression models) on the basis of the engineering of structural, electronic, and device descriptors for a dataset containing 351 D/A pairs showed the best prediction accuracy ( r > 0.8).…”

“…Driven by the development of artificial intelligence (AI) [ 10 ] algorithms, as well as the increased availability of a high‐quality large dataset along with efficient data‐mining techniques, [ 11 ] machine learning (ML) approaches have successfully resolved the difficulties of modeling the relationships between materials properties and complex chemical/physical factors [4c,12] . In recent years, ML techniques in conjunction with computational chemistry have been used to construct QSPR models to shed light on OPVs [4c,13] . Efficiency prediction accuracy has been raised to promising levels (e.g., r > 0.7) using different ML algorithms either in fullerene or nonfullerene‐based OPV devices.…”

Computational and data driven molecular material design assisted by low scaling quantum mechanics calculations and machine learning

“…For example, a new ML framework for simultaneously optimizing D/A molecule pairs and device specifications of OSCs is proposed. 210 The structural and electronic properties were further combined with the device bulk properties, which can be measured by atomic force microscope (AFM) experiments. In this way, the built QSPR model achieved unprecedentedly high accuracy and consistency.…”