SurfaceScience21 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
O: Fachverband Oberflächenphysik
O 55: Poster Session IV: Poster to Mini-Symposium: Machine learning applications in surface science II
O 55.2: Poster
Dienstag, 2. März 2021, 13:30–15:30, P
Materials genes of heterogeneous catalysis from clean experiments and AI — •Lucas Foppa1,2, Luca M. Ghiringhelli1,2, Frank Rosowski3, Robert Schloegl1,4, Annette Trunschke1, and Matthias Scheffler1,2 — 1Fritz-Haber-Institut der Max-Planck-Gesellschaft — 2Humboldt-Universität zu Berlin — 3BASF SE — 4Max-Planck-Institut für Chemische Energiekonversion
Heterogeneous catalysis is an example of a complex materials function, governed by an intricate interplay of several processes, e.g. the dynamic re-structuring of the catalyst material at reaction conditions and different surface chemical reactions. Modelling the full catalytic progression via first-principles statistical mechanics is impractical, if not impossible. Instead, we show here how an artificial-intelligence approach can be applied, even to an extremely small number of materials, to model catalysis and determine the key descriptive parameters (materials genes) reflecting the processes that trigger, facilitate, or hinder the catalyst performance. We start from a consistent, unparalleled experimental set of "clean data", containing nine vanadium-based oxidation catalysts which were carefully synthesized, fully characterized, and tested according to standardized protocols.[1] By applying the symbolic-regression SISSO approach,[2,3] we identify correlations between the few most relevant materials properties and their reactivity. This approach highlights the underlying physico-chemical processes, and accelerates catalyst design. [1] A. Trunschke, et al., Top. Catal. 63, 1683 (2020). [2] R. Ouyang et al., Phys. Rev. Mater. 2, 083802 (2018). [3] R. Ouyang et al., J. Phys. Mater. 2, 024002 (2019).