Discovery of all-inorganic lead-free perovskites with high photovoltaic performance via ensemble machine learning.

Abstract

Growing evidence shows that all-inorganic lead-free perovskites hold promise for solving stability and toxicity problems in perovskite solar cells. However, the power conversion efficiency of all-inorganic perovskites cannot match that of hybrid organic-inorganic perovskites. To face the challenges of efficiency, stability and toxicity simultaneously for application in perovskite solar cells, this study conducts a high-throughput materials search via ensemble machine learning for nearly 12 million all-inorganic perovskites to obtain candidates with non-toxicity and excellent photovoltaic performance. Based on experimental data, models for structure identification and band gap classification are established for , and a physics-inspired multi-component neural network is proposed as part of the exploration of the model's logical structure. It is found that extracting key features for input into the model and treating non-key features as supplements make model learning easier and are more effective in reducing the model parameters. Then, based on established ensemble models as well as the new criteria of ion radius difference and the optimization rules of toxicity and cost, over 80 000 candidates are screened. Among the 34 lead-free identified with suitable band gaps and negative formation energies through first principles calculations, 17 candidates have theoretical power conversion efficiencies over 20%. The Debye temperature of 10 lead-free , basically Bi-based compounds, is greater than 350 K, which is advantageous for suppressing nonradiative recombination and thermally induced degradation.