Kristian Sommer Thygesen (DTU): Data-Driven Materials Design

Kristian Sommer Thygesen (Technical University of Denmark): Data-Driven Materials Design TACO Colloquium on April 17, 2023. Abstract: Automated workflows for data generation and -exploitation (supervised and unsupervised) have long been employed in fields like biochemistry and drug discovery, but are only now making their way into materials science. I will begin this talk by introducing the Atomic Simulation Recipes (ASR) – an open-source Python framework for constructing and executing materials simulation workflows [https://doi.org/10.21105/joss.01844, https://iopscience.iop.org/article/10.1088/1361-648X/aa680e]. Next, I will give some examples of its use in materials design studies including the search for indirect band gap semiconductors for thin-film photovoltaics [https://doi.org/10.1021/jacs.2c07567] and the Computational 2D Materials Database (C2DB), which contains calculated properties of several thousand 2D materials in monolayer and bilayer form [https://iopscience.iop.org/article/10.1088/2053-1583/ac1059]. Finally, I will discuss how deep generative models can help to suggest new types of materials by learning the patterns in known data sets of stable materials [https://doi.org/10.1038/s41524-022-00923-3]. If time allows, I will discuss machine learning of GW band structures from descriptors encoding the electronic structure of standard DFT calculations [https://doi.org/10.1038/s41467-022-28122-0]. Bio: Prof. Thygesen develops and applies first-principles methods based on density functional theory and many-body perturbation theory to describe the electronic structure of materials with a particular focus on low-dimensional materials. He is also interested in data-driven approaches to materials design and the development of automated high-throughput workflow software. Prof. Thygesen received his Ph.D. from the Technical University of Denmark (DTU) in 2005. Today, he is heading the section for Computational Atomic-scale Materials Design (CAMD) at DTU, which is home to core developers of the GPAW electronic structure code and the Atomic Simulation Environment (ASE). He is involved in a number of international research projects including the EU Center of Excellence NOMAD.