The adsorption and self-organisation of organic molecules at inorganic surfaces is central to many industrial processes from catalysis and coatings, to organic electronics and solar cells. Computer simulations can help identify interface morphology and functionality, but sampling many atomic configurations over large length scales is prohibitively costly. We combined Bayesian optimisation  with accurate atomistic simulations in our efficient structure search tool BOSS, designed for smart probabilistic sampling of atomic configurations. The nearly parameter-free framework relies on Gaussian processes to construct a probable potential energy surface, which is then iteratively refined by input of energy data points from selected configurations.
We employed the BOSS framework in up to six dimensions to identify the optimal adsorption structures of large organic molecules on functional oxide substrates (e.g. coronene on Cu(110)-O p(2x1) or C60 on TiO2(101)). We report a dramatic speed-up in identifying optimal configurations, compared to the traditional chemical intuition technique, without significant loss of accuracy. Thanks to the smart Bayesian sampling scheme (balancing exploitation and exploration steps) and a streamlined ”building block” approach to molecular structure, even complex interface problems can be solved for relevant global and local minima structures .
 M. U. Gutmann, J. Corander, J. Mach. Learn. Res. 17, 1 (2016).
 M.Todorovic´, M. U. Gutmann, J. Corander and P. Rinke, arXiv:1708.09274
Back to Workshop I: Optimization and Optimal Control for Complex Energy and Property Landscapes