Machine Learning Stability and Bandgaps of Lead‐Free Perovskites for Photovoltaics. Issue 1 (18th November 2019)

• Record Type: Journal Article
• Authors: Stanley, Jared C.; Mayr, Felix; Gagliardi, Alessio
• Is Part Of: Advanced theory and simulations. Volume 3:Issue 1(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-11-18
• Subjects: density functional theory -- feature engineering -- lead‐free perovskites -- machine learning -- materials prediction; Science -- Simulation methods -- Periodicals; Science -- Methodology -- Periodicals; Engineering -- Simulation methods -- Periodicals; Engineering -- Methodology -- Periodicals; 507.21
• DOI: 10.1002/adts.201900178
• Languages: English
• ISSNs: 2513-0390

Abstract

Abstract: Compositional engineering of perovskites has enabled the precise control of material properties required for their envisioned applications in photovoltaics. However, challenges remain to address efficiency, stability, and toxicity simultaneously. Mixed lead‐free and inorganic perovskites have recently demonstrated potential for resolving such issues but their composition space is gigantic, making it difficult to discover promising candidates even using high‐throughput methods. A machine learning approach employing a generalized element‐agnostic fingerprint is shown to rapidly and accurately predict key properties using a new database of 344 perovskites generated with density functional theory. Bandgap, formation energy, and convex hull distance are predicted using validation subsets to within 146 meV, 15 meV per atom, and 11 meV per atom, respectively. The resulting model is used to predict trends in entirely different chemical spaces, and perform rapid composition and configuration space sampling without the need for expensive ab initio simulations. Abstract : Compositional engineering of perovskites enables precise control of material properties, facilitating creation of improved photovoltaics devices. A machine learning approach based on a generalized fingerprint is employed to predict key properties for photovoltaics. Trained on a computational database of lead‐free perovskites, validation yields errors comparable to DFT and the ability to rapidly sample compositional space is demonstrated.