Regensburg 2016 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
O: Fachverband Oberflächenphysik
O 88: Frontiers of Electronic Structure Theory: Focus on Topology and Transport V
O 88.5: Talk
Thursday, March 10, 2016, 16:00–16:15, H24
Representing energy landscapes by combining neural networks and the empirical valence bond method — •Sinja Klees1, Ramona Ufer2, Volodymyr Sergiievskyi2, Eckhard Spohr2, and Jörg Behler1 — 1Lehrstuhl für Theoretische Chemie, Ruhr-Universität Bochum, D-44780 Bochum, Germany — 2Lehrstuhl für Theoretische Chemie, Universität Duisburg-Essen, D-45141 Essen, Germany
In recent years, artificial neural networks (NNs) have become a powerful method to develop reactive interatomic potentials for large systems. However, the construction of NN potentials can become computationally very demanding due to the high dimensionality of the configuration space, which needs to be mapped by reference electronic structure calculations. Combining NN potentials with the empirical valence bond (EVB) method offers a promising approach to derive the potential energy of complex systems with substantially reduced effort, since the size of the reference structures can be strongly decreased. Preliminary results will be discussed and compared to density functional theory data.