Surrogate Modeling in the Evolutionary Optimization of Catalytic Materials

0380963 - ÚI 2013 RIV US eng C - Conference Paper (international conference)
Holeňa, Martin - Linke, D. - Bajer, Lukáš
Surrogate Modeling in the Evolutionary Optimization of Catalytic Materials.
GECCO '12. Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference. New York: ACM, 2012 - (Soule, T.), s. 1095-1102. ISBN 978-1-4503-1177-9.
[GECCO 2012. Genetic and Evolutionary Computation Conference. Conference on Genetic Algorithms /21./ and Annual Genetic Programming Conference /17./. Philadelphia (US), 07.07.2012-11.07.2012]
R&D Projects: GA ČR GA201/08/0802; GA ČR GAP202/11/1368
Grant - others:GA UK(CZ) 278511/2011
Institutional support: RVO:67985807
Keywords : evolutionary optimization * mixed optimization * surrogate modeling * model suitability * applications in chemistry
Subject RIV: IN - Informatics, Computer Science

The search for best performing catalysts leads to high-dimensional optimization tasks. They are by far most frequently tackled using evolutionary algorithms, usually implemented in systems developed specifically for the area of catalysis. Their fitness functions are black-box functions with costly and time-consuming empirical evaluation. This suggests to apply surrogate modeling. The paper points out three difficulties challenging the application of surrogate modeling to catalysts optimization: mixed-variables optimization, assessing the suitability of different models, and scalarization of multiple objectives. It then provides examples of how those challenges are tackled in real-world catalysts optimization tasks. The examples are based on results obtained in three such tasks using one of specific evolutionary optimization systems for catalysis.
Permanent Link: http://hdl.handle.net/11104/0211545