Proceedings of Internet Conference on Theory and Computation of Halide Perovskites (ComPer)
Publication date: 4th September 2020
Data-driven approaches have accelerated materials discovery along with the upsurge of machine learning (ML) applications, big data, and the adoption of computer science tools in materials science. I will give an overview of the latest advances in this field with a focus on the advances we made in the last few years applied to energy materials. I will show how a combination of high throughput density functional theory (DFT) calculation with machine learning is used to perform a systematic analysis of the structure-to-property relation exploring hybrid ABC3 Chalcogenide (I-V-VI3), Halide (I-II-VII3) perovskites. Focusing on the relationship between the BC6 octahedral deformations and the thermodynamic stability of the compounds, various Machine learning algorithms are trained then tested. I will also highlight how our approach [1-4] offers an interesting guideline on how to engineer mix-phase perovskites enabling to reduce the huge space of experimental trial and error of mixed anion and cation perovskites.
This work is sponsored by the Qatar National Research Fund (QNRF) through the National Priorities Research Program (NPRP8-090-2-047) and by the Qatar Environment and Energy Research Institute. Computational resources have been provided by the research computing group at Texas A&M University at Qatar. We are grateful to QEERI core labs for the XRD and SEM characterizations.