Automated Machine Learning Approach in Material Discovery of Hole Selective Layers for Perovskite Solar Cells

In the emerging field of perovskite solar cells, rational hole selective layer development is considered a double engine of this progress. To tap into the full potential and accelerate the commercialization path, machine learning (ML) is being tasked for perovskite screening. However, sincere efforts have not led to the design of hole selective layers based on the different organic core groups to yield efficient solar cells. Herein, it is demonstrated how ML can be applied to the advancement of hole transport materials (HTMs). The influence of HTMs with various core groups on the optoelectronic features and photovoltaic performance is evaluated and it is validated using both the random forest model and AutoML framework, General Automated Machine Learning Assistant (GAMA). To this end, the GAMA is utilized to predict the suitability of HTMs and it returns a 0.0542 ± 0.0470 RMSE score for 15 different materials on average. Correlation between experimental and predicted results is established, and GAMA is implemented for HTM suitability prediction. This paves the way for judicious and effective ways of the development of HTMs. In particular, the prediction approach from GAMA is an effective, reliable, and fast methodology and is pioneering in the field of HTM screening.