Artificial Intelligence Designer for Highly-Efficient Organic Photovoltaic Materials

Physics-Informed Machine Learning with Data-Driven Equations for Predicting Organic Solar Cell Performance

Organic solar cells (OSCs) have emerged as a promising solution in pursuing sustainable energy. This study presents a comprehensive approach to advancing OSC development by integrating data-driven equations from quantum mechanical (QM) descriptors with physics-informed machine learning (PIML) models. We circumvent traditional experimental limitations through high-throughput QM calculations, prioritizing transparent and interpretable models. Using the SISSO++ method, we identified key descriptors that effectively map the relationships between input variables and photovoltaic performance metrics. Our innovative predictive models, derived from SISSO outputs, excel in forecasting critical OSC parameters such as short-circuit current (JSC), open-circuit voltage (VOC), fill factor (FF), and power conversion efficiency (PCEmax), achieving high accuracy even with limited data sets. To validate our models' practical utility, we applied the PIML framework to a newly compiled data set of OSC devices, demonstrating their versatility and capability in pinpointing high-performance materials. This research underscores the strong predictive power of our models, bridging the gap between experimental results and theoretical predictions and making significant contributions to the advancement of sustainable energy technologies.

Polymer-Unit Fingerprint (PUFp): An Accessible Expression of Polymer Organic Semiconductors for Machine Learning

High-performance organic semiconductors (OSCs) can be designed based on the identification of functional units and their role in the material properties. Herein, we present a polymer-unit fingerprint (PUFp) generation framework, "Python-based polymer-unit-recognition script" (PURS), to identify the subunits "polymer unit" in the polymer and generate polymer-unit fingerprint (PUFp). Using 678 collected OSC data, machine learning (ML) models can be used to determine structure-mobility relationships by using PUFp as a structural input, and the classification accuracy reaches 85.2%. A polymer-unit library consisting of 445 units is constructed, and the key polymer units affecting the mobility of OSCs are identified. By investigating the combinations of polymer units with mobility performance, a scheme for designing OSCs by combining ML approaches and PUFp information is proposed. This scheme not only passively predicts OSC mobility but also actively provides structural guidance for high-mobility OSC material design. The proposed scheme demonstrates the ability to screen materials through pre-evaluation and classification ML steps and is an alternative methodology for applying ML in high-mobility OSC discovery.

Active Discovery of Donor:Acceptor Combinations For Efficient Organic Solar Cells

The structural flexibility of organic semiconductors offers vast a search space, and many potential candidates (donor and acceptor) for organic solar cells (OSCs) are yet to be discovered. Machine learning is extensively used for material discovery but performs poorly on extrapolation tasks with small training data sets. Active learning techniques can guide experimentalists to extrapolate and find the most promising D:A combination in a significantly small number of experiments. This study uses an active learning technique with a predictive random forest model to iteratively find the most optimal D:A combinations in the search space using various acquisition functions. Active learning results with five different acquisition functions (MM, MEI, MLI, MU, and UCB) are compared. Results reveal that acquisition functions that combine exploitation and exploration (MEI, MLI, and UCB) perform far better than purely exploiting (MM) and purely exploring (MU) acquisition functions. Interestingly, the proposed model can overcome the bottleneck of extrapolating small training data sets and find most promising D:A combinations in relatively fewer experiments.

High-Efficiency Non-Fullerene Acceptors Developed by Machine Learning and Quantum Chemistry

Y6 and its derivatives have greatly improved the power conversion efficiency (PCE) of organic photovoltaics (OPVs). Further developing high-performance Y6 derivative acceptor materials through the relationship between the chemical structures and properties of these materials will help accelerate the development of OPV. Here, machine learning and quantum chemistry are used to understand the structure-property relationships and develop new OPV acceptor materials. By encoding the molecules with an improved one-hot code, the trained machine learning model shows good predictive performance, and 22 new acceptors with predicted PCE values greater than 17% within the virtual chemical space are screened out. Trends associated with the discovered high-performing molecules suggest that Y6 derivatives with medium-length side chains have higher performance. Further quantum chemistry calculations reveal that the end acceptor units mainly affect the frontier molecular orbital energy levels and the electrostatic potential on molecular surface, which in turn influence the performance of OPV devices. A series of promising Y6 derivative candidates is screened out and a rational design guide for developing high-performance OPV acceptors is provided. The approach in this work can be extended to other material systems for rapid materials discovery and can provide a framework for designing novel and promising OPV materials.

Machine Learning-Assisted Development of Organic Solar Cell Materials: Issues, Analyses, and Outlooks

Nonfullerene, a small molecular electron acceptor, has substantially improved the power conversion efficiency of organic photovoltaics (OPVs). However, the large structural freedom of π-conjugated polymers and molecules makes it difficult to explore with limited resources. Machine learning, which is based on rapidly growing artificial intelligence technology, is a high-throughput method to accelerate the speed of material design and process optimization; however, it suffers from limitations in terms of prediction accuracy, interpretability, data collection, and available data (particularly, experimental data). This recognition motivates the present Perspective, which focuses on utilizing the experimental data set for ML to efficiently aid OPV research. This Perspective discusses the trends in ML-OPV publications, the NFA category, and the effects of data size and explanatory variables (fingerprints or Mordred descriptors) on the prediction accuracy and explainability, which broadens the scope of ML and would be useful for the development of next-generation solar cell materials.