Insights from Machine Learning Techniques for Predicting the Efficiency of Fullerene Derivatives‐Based Ternary Organic Solar Cells at Ternary Blend Design

Abstract

Ternary organic solar cells (OSCs) have progressed significantly in recent years due to the sufficient photon harvesting of the blend photoactive layer including three absorption‐complementary materials. With the rapid development of highly efficient ternary OSCs in photovoltaics, the precise energy‐level alignment of the three active components within ternary OSC devices should be taken into account. The machine‐learning technique is a computational method that can effectively learn from previous historical data to build predictive models. In this study, a dataset of 124 fullerene derivatives‐based ternary OSCs is manually constructed from a diverse range of literature along with their frontier molecular orbital theory levels, and device structures. Different machine‐learning algorithms are trained based on these electronic parameters to predict photovoltaic efficiency. Thus, the best predictive capability is provided by using the Random Forest approach beyond other machine‐learning algorithms in the dataset. Furthermore, the Random Forest algorithm yields valuable insights into the crucial role of lowest unoccupied molecular orbital energy levels of organic donors in the performance of ternary OSCs. The outcome of this study demonstrates a smart strategy for extracting underlying complex correlations in fullerene derivatives‐based ternary OSCs, thereby accelerating the development of ternary OSCs and related research fields.

A Machine Learning–Based Design Rule for Improved Open‐Circuit Voltage in Ternary Organic Solar Cells

“…At first, the 121 V oc data points were collected as an available dataset from recently reported review articles . A total of 121 fullerene derivative‐based ternary OSCs (26 polymer donors and 90 third components) were trained in the study.…”

Machine learning for accelerating the discovery of high-performance donor/acceptor pairs in non-fullerene organic solar cells

“…Some ML approaches have been introduced into the OSCs for the screening of complex molecules and their PCE prediction of relevant photovoltaic systems [33][34][35][36][37][38][39][40] . For instance, Sun et al 33 developed a deep learning model based on a convolutional neural network (CNN) that enables recognition of chemical structures and automatic classification for predicting the PCE of D materials.…”

“…Shinji et al reported a screening of conjugated molecules for polymer-fullerene OSC applications with artificial neural network (ANN) and random forest (RF) algorithms by importing parameters such as PCE, molecular weight, energy levels, and electronic properties with digitized chemical structures 36 . However, these examples of the application of ML algorithms were mostly used in the fullerene-based OSCs, whereas the reports about the application of ML algorithms in the non-fullerene-based OSCs are limited [41][42][43] . As non-fullerene acceptors (NFAs) draw researchers' attention and have become research hotspots [44][45][46] , and most state of art OSCs with efficiency up to 13-17% were achieved by NFA OSCs in these few years 4,47,48 , we shoud pay more attention to the applications of ML approaches that would tackle broader and more complex non-fullerene OSCs.…”

Machine Learning Assisted Synthesis of Metal–Organic Nanocapsules

“…It is proposed that the lower accuracy of the XGB model when predicting 20 new validation experiments may be due to insufficient generalization of the developed XGB model which is more or less influenced by a few potential exceptions (e.g., rare items in a majority of data). [45][46] Nevertheless, we believe that as the first proof-of-concept for predicting the crystallization propensity of MONCs the XGB model shows great potentials in guiding chemists, especially new entrants, to screen the reaction parameters for synthesizing new MONCs single-crystal.…”