Bayesian regression for
multi-level machine-learned potentials

Subproject P03

The first-principles description of the properties of multi-component metal oxides is an exceedingly challenging problem. The reasons are that the configurational space grows exponentially with the number of species and standard Density Functional Theory (DFT) is often not accurate enough. The long-term objective of P03 is to accelerate first-principles calculations by developing machine-learning approaches for the description of the interatomic forces, Born effective charges, and other tensorial properties of multivalent oxides. The project will rely on kernel-based methods and Bayesian inference to implement fully automatic “on-the-fly” learning.

In the first project period, we will develop machine-learned force fields (MLFF) for DFT and DFT+U, whereby the number of components in the FF will be gradually increased. A concise framework for learning tensorial properties will be implemented. We will use this to simulate infrared spectra of oxide materials, which can be readily compared to the finite-temperature spectra measured by the experimental groups.

The difference between DFT and hybrid functionals will be machine-learned to go beyond semi-local functionals (Delta-learning). The long-term perspective is to extend this approach to highly accurate beyond-DFT methods, such as the random phase approximation and quantum chemistry (coupled cluster) methods. Although kernel-based methods are exceedingly accurate, they are often less efficient than NN. We will collaborate with other projects to recast the on-the-fly trained FF into NN potentials to address this issue.

Georg Kresse
PI

Expertise

The main research efforts of the group are directed towards the development of quantum-mechanical tools for atomic-scale simulations of properties and processes in materials and the application of these methodologies to key areas of condensed matter physics and materials research. An important pillar of the research is the Vienna Ab initio Simulation Package (VASP), a general-purpose ab initio code for solving the many-electron Schrödinger equation. The code is among the world leaders in its field, with more than 3500 licensees worldwide. We have expertise with simulations for a vast number of properties using many different techniques:

  • Density functional theory (DFT), including spin and non-collinear DFT
  • Linear response theory to calculate phonons and dielectric properties
  • Hartree-Fock techniques and many flavors of hybrid functionals
  • Many-body perturbation theory, including GW and Bethe-Salpeter
  • Wavefunction-based correlated methods (Møller-Plesset perturbation theory)
  • Surface science, including growth and oxide formation
  • Simulation of nanostructures
  • Semiconductor physics: charge trapping, polarons
  • Electronic excitations
  • Defect energies in extended systems

For TACO, we will adapt our machine-learning techniques to tensorial properties and correlated wavefunction techniques. These techniques are directly integrated into VASP and allow to accelerate finite-temperature simulations by many orders of magnitudes.

Team

Georg Kresse
PI

Bernhard Schmiedmayer
PhD Student

Carolin Faller
PhD Student,
Student Representative

Former Members

Carla Verdi
co-PI

Peitao Liu
PostDoc

Publications

Show all

22 entries « 1 of 3 »

2023

Hematite α-Fe2O3(0001) in Top and Side View: Resolving Long-Standing Controversies about Its Surface Structure

Redondo, Jesús; Michalička, Jan; Kraushofer, Florian; Franceschi, Giada; Šmid, Břetislav; Kumar, Nishant; Man, Ondřej; Blatnik, Matthias; Wrana, Dominik; Mallada, Benjamin; Švec, Martin; Parkinson, Gareth S.; Setvin, Martin; Riva, Michele; Diebold, Ulrike; Čechal, Jan

Hematite α-Fe2O3(0001) in Top and Side View: Resolving Long-Standing Controversies about Its Surface Structure

Journal ArticleOpen Access

In: Advanced Materials Interfaces, no. 2300602, 2023.

Abstract | Links | BibTeX | Tags: P02, P04

Oxygen-Terminated (1 × 1) Reconstruction of Reduced Magnetite Fe3O4(111)

Kraushofer, Florian; Meier, Matthias; Jakub, Zdeněk; Hütner, Johanna; Balajka, Jan; Hulva, Jan; Schmid, Michael; Franchini, Cesare; Diebold, Ulrike; Parkinson, Gareth S.

Oxygen-Terminated (1 × 1) Reconstruction of Reduced Magnetite Fe3O4(111)

Journal ArticleOpen Access

In: vol. 14, no. 13, pp. 3258–3265, 2023.

Abstract | Links | BibTeX | Tags: P02, P04, P07

Automated Real-Space Lattice Extraction for Atomic Force Microscopy Images

Corrias, Marco; Papa, Lorenzo; Sokolovíc, Igor; Birschitzky, Viktor; Gorfer, Alexander; Setvin, Martin; Schmid, Michael; Diebold, Ulrike; Reticcioli, Michele; Franchini, Cesare

Automated Real-Space Lattice Extraction for Atomic Force Microscopy Images

Journal ArticleOpen Access

In: Machine Learning: Science and Technology, vol. 4, pp. 015015, 2023.

Abstract | Links | BibTeX | Tags: P02, P07

2022

Surface chemistry on a polarizable surface: Coupling of CO with KTaO 3(001)

Wang, Zhichang; Reticcioli, Michele; Jakub, Zdenek; Sokolović, Igor; Meier, Matthias; Boatner, Lynn A; Schmid, Michael; Parkinson, Gareth S.; Diebold, Ulrike; Franchini, Cesare; Setvin, Martin

Surface chemistry on a polarizable surface: Coupling of CO with KTaO 3(001)

Journal ArticleOpen Access

In: Science Advances, vol. 8, iss. 33, 2022.

Abstract | Links | BibTeX | Tags: P02, P04, P07

Competing electronic states emerging on polar surfaces

Reticcioli, Michele; Wang, Zhichang; Schmid, Michael; Wrana, Dominik; Boatner, Lynn A.; Diebold, Ulrike; Setvin, Martin; Franchini, Cesare

Competing electronic states emerging on polar surfaces

Journal ArticleOpen Access

In: Nature Communications, vol. 13, no. 4311, 2022.

Abstract | Links | BibTeX | Tags: P02, P07

Machine learning for exploring small polaron configurational space

Birschitzky, Viktor C; Ellinger, Florian; Diebold, Ulrike; Reticcioli, Michele; Franchini, Cesare

Machine learning for exploring small polaron configurational space

Journal ArticleOpen Access

In: npj Computational Materials, vol. 8, no. 125, 2022.

Abstract | Links | BibTeX | Tags: P02, P07

Structure of an Ultrathin Oxide on Pt3Sn(111) Solved by Machine Learning Enhanced Global Optimization

Merte, Lindsay R; Bisbo, Malthe Kjær; Sokolović, Igor; Setvín, Martin; Hagman, Benjamin; Shipilin, Mikhail; Schmid, Michael; Diebold, Ulrike; Lundgren, Edvin; Hammer, Bjørk

Structure of an Ultrathin Oxide on Pt3Sn(111) Solved by Machine Learning Enhanced Global Optimization

Journal ArticleOpen Access

In: Angewandte Chemie - International Edition, vol. 61, iss. 25, pp. e202204244, 2022.

Abstract | Links | BibTeX | Tags: P02

CO oxidation by Pt2/Fe3O4: Metastable dimer and support configurations facilitate lattice oxygen extraction

Meier, Matthias; Hulva, Jan; Jakub, Zdenek; Kraushofer, Florian; Bobić, Mislav; Bliem, Roland; Setvin, Martin; Schmid, Michael; Diebold, Ulrike; Franchini, Cesare; Parkinson, Gareth S.

CO oxidation by Pt2/Fe3O4: Metastable dimer and support configurations facilitate lattice oxygen extraction

Journal ArticleOpen Access

In: ScienceAdvances, vol. 8, iss. 13, pp. eabn4580, 2022.

Abstract | Links | BibTeX | Tags: P02, P04, P07

Modeling polarons in density functional theory: lessons learned from TiO2

Reticcioli, Michele; Diebold, Ulrike; Franchini, Cesare

Modeling polarons in density functional theory: lessons learned from TiO2

Journal ArticleOpen Access

In: Journal of Physics: Condensed Matter, vol. 34, no. 20, pp. 204006, 2022.

Abstract | Links | BibTeX | Tags: P02, P07

Reconstruction changes drive surface diffusion and determine the flatness of oxide surfaces

Franceschi, Giada; Schmid, Michael; Diebold, Ulrike; Riva, Michele

Reconstruction changes drive surface diffusion and determine the flatness of oxide surfaces

Journal ArticleOpen Access

In: Journal of Vacuum Science & Technology A, vol. 40, no. 2, pp. 023206, 2022.

Abstract | Links | BibTeX | Tags: P02

22 entries « 1 of 3 »