Deep Transfer Learning: A Fast and Accurate Tool to Predict the Energy Levels of Donor Molecules for Organic Photovoltaics. Issue 5 (23rd February 2022)

• Record Type: Journal Article
• Authors: Moore, Gareth John; Bardagot, Olivier; Banerji, Natalie
• Is Part Of: Advanced theory and simulations. Volume 5:Issue 5(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-02-23
• Subjects: convolutional neural network -- deep learning -- density functional theory -- organic photovoltaics -- transfer learning; Science -- Simulation methods -- Periodicals; Science -- Methodology -- Periodicals; Engineering -- Simulation methods -- Periodicals; Engineering -- Methodology -- Periodicals; 507.21
• DOI: 10.1002/adts.202100511
• Languages: English
• ISSNs: 2513-0390

Abstract

Abstract: Molecular engineering is driving the recent efficiency leaps in organic photovoltaics (OPVs). A presynthetic determination of frontier energy levels makes the screening of potential molecules more efficient, exhaustive, and cost‐effective. Here, a convolutional neural network is developed to predict the highest occupied and lowest unoccupied molecular orbital (HOMO/LUMO) levels of donor molecules for OPV. The model takes a 2D structure image and returns a prediction of its HOMO/LUMO levels comparable to experimental values. Insufficient experimental datasets are overcome with transfer learning where the model is initially trained on the large Harvard Clean Energy Project dataset and then fine‐tuned using experimental data from the Harvard Organic Photovoltaic dataset. Error margins on predicted HOMO/LUMO levels below 200 meV are achieved, without any chemical knowledge implemented. Noticeably, the model outputs have higher accuracy and precision than corresponding density functional theory (DFT) estimations. The model and its limitations are further tested on a home‐built dataset of commercially available donor polymers reported in OPVs (e.g., P3HT, PTB7‐Th, PM6, D18). The results demonstrate both the practical utility of this model, to foster rational molecular engineering for OPV optimization, and the potential for deep learning techniques, in general, to revolutionize the energy materials research and development sector. Abstract : A deep convolutional neural network is developed to predict HOMO/LUMO energies of donor molecules, for organic photovoltaic applications, from images of their structures. The model is trained using a large DFT based dataset and fine‐tuned on an experimentally based dataset using transfer learning. The resulting model shows superior predictivity than traditional DFT simulations, within well‐defined limitations.