Virtual Screening of Conjugated Polymers for Organic Photovoltaic Devices Using Support Vector Machines and Ensemble Learning

Abstract

Herein, we report virtual screening of potential semiconductor polymers for high-performance organic photovoltaic (OPV) devices using various machine learning algorithms. We particularly focus on support vector machine (SVM) and ensemble learning approaches. We found that the power conversion efficiencies of the device prepared with the polymer candidates can be predicted with their structure fingerprints as the only inputs. In other words, no preliminary knowledge about material properties was required. Additionally, the predictive performance could be further improved by “blending” the results of the SVM and random forest models. The resulting ensemble learning algorithm might open up a new opportunity for more precise, high-throughput virtual screening of conjugated polymers for OPV devices.

Instantaneous Property Prediction and Inverse Design of Plasmonic Nanostructures Using Machine Learning: Current Applications and Future Directions

“…Zhu et al demonstrated a bi-directional ensemble network for metasurface design which yields a prediction MSE significantly less than that of single DNN and Resnet models [127]. Though ensemble learning is a fairly new technique in designing plasmonic devices, its application in optics [128] and photovaltaics [129] implies its usefulness in the plasmonics field.…”

Opportunities and challenges for machine learning to select combination of donor and acceptor materials for efficient organic solar cells

“…Saeki et al 66 in 2018 created a FA based dataset of 1200 OSCs with polymer donors for PCE prediction, and the same approach was used by Wei et al 67 for 500 NFA based OSCs. In 2019, Chen 68 used the 1200 dataset by Saeki et al 66 for virtual screening of conjugated polymers. In 2019, Troisi et al 69 and Ma et al 70 created FA datasets of 249 and 300 OSCs with small molecule donors.…”

“…Chen 68 used a dataset of 1203 polymer–fullerene OSCs by Saeki et al 66 for virtual screening using RF and SVM models. Using RDKit, 118 morgan fingerprints 117 were calculated as input descriptors, and the use of morgan radius further improved the model accuracy.…”

Directed Message Passing Neural Network for Predicting Power Conversion Efficiency in Organic Solar Cells

“…The integration of ML models into the field of OSCs has opened up new avenues for exploring the vast chemical space with greater efficiency and cost-effectiveness. − With the rapid advancement of ML techniques, scientists are now empowered to delve deeper into the properties of chemical systems, taking advantage of the abundance of data, improved algorithms, and exponential increases in computational power . In the field of OSCs, various ML models have been used for predicting key performance metrics such as PCE, − short circuit current density ( J SC ), open-circuit voltage ( V OC ), ,,, fill factor, , non-radiative voltage loss (Δ V NR ), and frontier molecular orbitals (FMO). , High-throughput screening has also become a valuable tool for identifying promising OSC candidates. The rapid progress of machine learning algorithms and the continuous advancement of computational power are helping researchers with materials design, discovery, and optimization.…”