Logo RUB
  • Institute
    • ICAMS
      • Mission
      • Structure
      • Members
    • Departments & Research Groups
      • Atomistic Modelling and Simulation
      • Scale-Bridging Thermodynamic and Kinetic Simulation
      • Micromechanical and Macroscopic Modelling
      • Artificial Intelligence for Integrated Material Science
      • Scale-Bridging Simulation of Functional Composites
      • Materials Informatics and Data Science
      • Theory of Excited States of Integrated Solid State Systems
      • High-Performance Computing in Materials Science
    • Advanced Study Groups
      • Ab Initio-Based Modelling
      • Input Data and Validation
      • Diffusion and Microstructure Analysis
      • Continuum Mechanics
      • Processing and Characterization
    • Central Services
      • Coordination Office
      • IT
  • Research
    • Overview
    • Publications
    • Software and Data
    • Collaborative research
    • Research networks
    • Young enterprises
  • Teaching
    • Overview
    • Materialwissenschaft B.Sc.
    • Materials Science and Simulation M.Sc.
    • ICAMS Graduate School
    • Student Projects
  • News & Events
    • Overview
    • News
    • Seminars and Workshops
    • Conferences
  • Services
    • Overview
    • Contact
    • Open positions
    • Travel information
 
ICAMS
ICAMS
MENÜ
  • RUB-STARTSEITE
  • Institute
    • ICAMS
    • Departments & Research Groups
    • Advanced Study Groups
    • Central Services
  • Research
    • Overview
    • Publications
    • Software and Data
    • Collaborative research
    • Research networks
    • Young enterprises
  • Teaching
    • Overview
    • Materialwissenschaft B.Sc.
    • Materials Science and Simulation M.Sc.
    • ICAMS Graduate School
    • Student Projects
  • News & Events
    • Overview
    • News
    • Seminars and Workshops
    • Conferences
  • Services
    • Overview
    • Contact
    • Open positions
    • Travel information
Home » Institute » Departments & Research Groups » Atomistic Modelling and Simulation » Data-Driven Methods for Atomistic Simulations

Just another WordPress site - Ruhr-Universität Bochum

Department Atomistic Modelling and Simulation
Research Group

Data-Driven Methods for Atomistic Simulations

The research group develops and applies data-driven methods in materials science, with a principal emphasis on atomic-scale simulations using the Atomic Cluster Expansion (ACE) – a new type of machine learning interatomic potentials with a formally complete basis set.


Yury LysogorskiyRUB, Marquard
Dr. Yury Lysogorskiy

Research Group Leader

Room: 02-719
Tel.: +49 234 32 29300
E-Mail: yury.lysogorskiy@icams.rub.de




Research

Our research covers the full cycle of ACE model parameterization and validation. This comprises extensions to the formalism, implementation in high-performance simulation codes, such as LAMMPS, parameterization of ACE using non-linear optimization with TensorFlow, uncertainty indication and active learning for selecting representative data. It also includes deploying high-throughput calculations for computing reference DFT energies and forces and workflows for validating interatomic potentials for accuracy and transferability.

Block scheme of the main pacemaker workflow.
Block scheme of the main pacemaker workflow.
ICAMS, RUB

Competences

  • Atomic Cluster Expansion (ACE): method development, parameterization and validation
  • High-throughput calculations (DFT and molecular dynamics)
  • Data-driven methods in materials science: machine learning, generative models
Members
  • Bochkarev, Dr. Anton
  • Ibrahim, M.Sc. Eslam
  • Lysogorskiy, Dr. Yury
  • Rinaldi, Dr. Matteo
Recent Publications
  • M. Rinaldi. Modelling magnetism from the electronic structure to continuum for iron and its alloys. PhD Thesis, Ruhr-Univerisität Bochum, (2022)
  • A. Bochkarev, Y. Lysogorskiy, S. Menon et al. Efficient parametrization of the atomic cluster expansion. Physical Review Materials, 6, 013804, (2022)
  • M. Rinaldi, M. Mrovec, M. Fähnle et al. Determination of spin-wave stiffness in the Fe-Si system using first-principles calculations. Physical Review B, 104, 064413, (2021)
  • S. Starikov, D. Smirnova, T. Pradhan et al. Angular-dependent interatomic potential for large-scale atomistic simulation of iron: development and comprehensive comparison with existing interatomic models. Physical Review Materials, 5, 063607, (2021)
  • Y. Lysogorskiy, C. van der Oord, A. Bochkarev et al. Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon. npj Computational Materials, 7, 97, (2021)
  • S. Amariamir. Combining active and transfer learning for data-guided search of new materials. Master Thesis, Ruhr-Universität Bochum, (2020)

Research Examples

Multilayer atomic cluster expansion for semi-local interactions

The multilayer atomic cluster expansion (ml-ACE) was presented, which includes collective, semi-local multiatom interactions naturally within its remit. It was demonstrated that ml-ACE significantly improves fit accuracy and efficiency compared to a local expansion on selected examples and provides physical intuition to understand this improvement.

Teaser B1
Performant implementation of the atomic cluster expansion (PACE): application to copper and silicon

We implemented the ACE in the performant C++ code PACE that is suitable for use in large-scale atomistic simulations with LAMMPS. It was demonstrated that the atomic cluster expansion as implemented in PACE shifts a previously established Pareto front for machine learning interatomic potentials toward faster and more accurate calculations.

Logo RUB
  • Open positions
  • Travel information
  • Imprint
  • Privacy Policy
  • Sitemap
Ruhr-Universität Bochum
Universitätsstraße 150
44801 Bochum

  • Open positions
  • Travel information
  • Imprint
  • Privacy Policy
  • Sitemap
Seitenanfang Kontrast N