International Summer School on AI and Big Data, Dr. Lucas Foppa (Fritz Haber Institute, Max-Planck-Gesellschaft) will talk about The “Genes” of Materials Properties and Functions Identified by Symbolic Regression. The keynote will take place on Wednesday, 06.07.2023 from 1:30 p.m. – 2:30 p.m.
The identification of correlations describing materials properties and functions is crucial for guiding materials discovery, since the number of possible materials is practically infinite and only few compounds are useful for a given application. However, the materials behaviour might result from an intricate interplay of several underlying physical processes, challenging the explicit modelling of materials by simulation and the derivation of these correlations.
In this talk, the combination of consistent experimental and theoretical data with symbolic regression is presented as an approach to model materials and to determine the key physicochemical descriptive parameters (“materials genes”) reflecting the processes that trigger, facilitate, or hinder the materials performance. The symbolic regression AI approach leverages the small number of materials that can be accessed experimentally and identifies nonlinear correlations that can be exploited for enhancing physical understanding and designing new materials. The data-centric approach is illustrated in the context of heterogeneous catalysis [1,2] and mechanical properties [3].
[1] L. Foppa, L. M. Ghiringhelli, F. Girgsdies, M. Hashagen, P. Kube, M. Hävecker, S. Carey, A. Tarasov, P. Kraus, F. Rosowski, R. Schlögl, A. Trunschke, and M. Scheffler, MRS Bull. 46, 1 (2021).
[2] L. Foppa, F. Rüther, M. Geske, G. Koch, F. Girgsdies, P. Kube, S. Carey, M. Hävecker, O. Timpe, A. Tarasov, M. Scheffler, F. Rosowski, R. Schlögl, and A. Trunschke, J. Am. Chem. Soc. 145, 3427 (2023).
[3] L. Foppa, T. A. R. Purcell, S. V. Levchenko, M. Scheffler, L. M. Ghiringhelli, Phys. Rev. Lett. 129, 055301 (2022).
Dr. Lucas Foppa received his PhD from ETH Zurich, where his research focused on first-principles modelling of nanoparticle catalysts. Then he moved to the Fritz Haber Institute of the Max Planck Society as a postoctoral researcher, where he worked on data-centric approaches for materials science. Since 2021, he is the head of the group “ab initio and AI methods for heterogeneous catalysis” at the Fritz Haber Institute and Humboldt-Universitat zu Berlin.