ICAMS / Interdisciplinary Centre for Advanced Materials Simulation

Data-driven methods for atomistic simulations

Yury Lysogorskiy

The research group is working on the application of data-driven methods in materials science with a particular focus on the atomic scale. A major research area is the automated extraction, analysis and validation of models in materials science, with specific application to interatomic potentials. We perform high-throughput calculations of materials properties at different levels of theory, including both density functional theory and effective interatomic potentials using the pyiron computational framework, which we co-develop with the Computational Materials Design department at the Max Planck Institute for iron research

Computational and data infrastructure for interatomic potentials validation. (Click image to enlarge.)

Another research area is the application of machine learning methods to large data sets, for example, from combinatorial or high-throughput methods and to provide efficient and supporting tools for materials discovery.

Pair plots of formation energies and band gaps of Al-Ga-In sesquioxides as calculated by density functional theory and predicted by surrogate machine learning models. (Click image to enlarge.)



  • data-driven methods (machine learning) in materials science
  • high-throughput calculations (DFT and molecular dynamics)
  • interatomic potentials and their validation
  • data management & visualization

Dr. Yury Lysogorskiy
Ruhr-Universität Bochum
44780 Bochum
Tel: +49 234 32 29300
Fax: +49 234 32 14977

Email: yury.lysogorskiy@icams.rub.de

Group Members


Recent publications

S. Starikov, I. Gordeev, Y. Lysogorskiy, L. Kolotova et al. Optimized interatomic potential for study of structure and phase transitions in Si-Au and Si-Al systems Computational Materials Science, 184, 109891, (2020)

S. Menon, G. Díaz Leines, R. Drautz, J. Rogal. Role of pre-ordered liquid in the selection mechanism of crystal polymorphs during nucleation The Journal of Chemical Physics, 153, 104508, (2020)

S. Amariamir. Combining active and transfer learning for data-guided search of new materials Master Thesis, Ruhr-Universität Bochum (2020)

L. Banko, Y. Lysogorskiy, D. Grochla, D. Naujoks et al. Predicting structure zone diagrams for thin film synthesis by generative machine learning Communications Materials, 1, 15, (2020)

A. Ferrari, M. F. Schröder, Y. Lysogorskiy, J. Rogal et al. Phase transitions in titanium with an analytic bond-order potential Modelling and Simulation in Materials Science and Engineering, 27, 085008, (2019)

« back