Machine-learning methods for structure prediction of multi-component perovskites

Subproject P09

The connection between the composition and function of complex multi-component oxides is intricate, and our knowledge about it is extremely limited. Current models can at most predict the stability of a stoichiometric composition, a very general structural feature. P09 will develop accelerated ML models to predict the structural details that determine the functionality of perovskites. We will implement two approaches:

First, EAs will be combined with an NN potential trained on the fly to quickly explore the energy landscape of perovskite surfaces and predict their detailed structures. In collaboration with experimental partners (P02 Diebold, P04 Parkinson), those structures will be falsified by direct comparison with diffraction data on existing surfaces. Additionally, the implementation, inputs, and results of the machine-learned force fields (MLFFs) will be shared with the theoretical partners for cross-validation.

Second, GANs will be trained on known compositions to identify the key features of real perovskite structures and propose new stable ones.

Georg Madsen
PI

Expertise

We develop and apply atomistic models for theoretical chemistry and materials science. Our expertise covers both classical and quantum methods, as well as multiscale calculations and machine-learning techniques. The group has taken part in the development and public release of a range of packages for atomistic calculations, including:

  • WIEN2k, a popular all-electron density functional theory implementation;
  • BoltzTraP and BoltzTraP2, two packages used to interpolate electronic band structures and calculate transport coefficients;
  • ShengBTE, the first open-source solver of the Boltzmann transport for phonons, which enables predictive calculations of the thermal conductivity of nanostructures;
  • almaBTE, a software package for multiscale thermal transport simulation based on first principles;
  • Clinamen, an implementation of the covariance matrix adaptation evolutionary algorithm that helps explore complex energy landscapes.

These are some of the methods we have used to study solids, liquids, surfaces, and nanostructures:

  • Density functional theory (DFT);
  • Classical and ab-initio molecular dynamics (MD);
  • Self-consistent anharmonic free energy calculations;
  • The Boltzmann transport equation (BTE);
  • Traditional and particle-filter Monte Carlo (MC);
  • Covariance matrix adaptation evolutionary algorithm (CMA-ES);
  • Classification and regression random forests based on phenomenological information;
  • Algorithmically differentiable machine-learning (ML) force fields based on JAX;
  • High-throughput (HT) materials screening.

Team

Georg Madsen
PI

Jesús Carrete
co-PI

Florian Buchner
PhD Student

Ralf Wanzenböck
PhD Student

Associates

Péter Kovács
PostDoc

Nico Unglert
PhD Student

Show all

43 entries « 2 of 5 »

2021

First-principles hydration free energies of oxygenated species at water–platinum interfaces

Jinnouchi, Ryosuke; Karsai, Ferenc; Verdi, Carla; Kresse, Georg

First-principles hydration free energies of oxygenated species at water–platinum interfaces

Journal Article

In: The Journal of Chemical Physics, vol. 154, no. 9, pp. 094107, 2021.

Abstract | Links | BibTeX | Tags: P03, pre-TACO

Unraveling CO adsorption on model single-atom catalysts

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

Unraveling CO adsorption on model single-atom catalysts

Journal Article

In: Science, vol. 371, no. 6527, pp. 375–379, 2021.

Abstract | Links | BibTeX | Tags: P02, P04, P07, pre-TACO

How the anisotropy of surface oxide formation influences the transient activity of a surface reaction

Winkler, Philipp; Zeininger, Johannes; Suchorski, Yuri; Stöger-Pollach, Michael; Zeller, Patrick; Amati, Matteo; Gregoratti, Luca; Rupprechter, Günther

How the anisotropy of surface oxide formation influences the transient activity of a surface reaction

Journal ArticleOpen Access

In: Nature Communications, vol. 12, no. 1, 2021.

Abstract | Links | BibTeX | Tags: P08, pre-TACO

Sum frequency generation spectroscopy in heterogeneous model catalysis: a minireview of CO-related processes

Li, Xia; Rupprechter, Günther

Sum frequency generation spectroscopy in heterogeneous model catalysis: a minireview of CO-related processes

Journal ArticleOpen Access

In: Catalysis Science & Technology, vol. 11, no. 1, pp. 12–26, 2021.

Abstract | Links | BibTeX | Tags: P08, pre-TACO

2020

Interplay between CO Disproportionation and Oxidation: On the Origin of the CO Reaction Onset on Atomic Layer Deposition-Grown Pt/ZrO2 Model Catalysts

Pramhaas, Verena; Roiaz, Matteo; Bosio, Noemi; Corva, Manuel; Rameshan, Christoph; Vesselli, Erik; Grönbeck, Henrik; Rupprechter, Günther

Interplay between CO Disproportionation and Oxidation: On the Origin of the CO Reaction Onset on Atomic Layer Deposition-Grown Pt/ZrO2 Model Catalysts

Journal ArticleOpen Access

In: ACS Catalysis, vol. 11, no. 1, pp. 208–214, 2020.

Abstract | Links | BibTeX | Tags: P08, P10, pre-TACO

An ultrahigh vacuum-compatible reaction cell for model catalysis under atmospheric pressure flow conditions

Haunold, Thomas; Rameshan, Christoph; Bukhtiyarov, Andrey V; Rupprechter, Günther

An ultrahigh vacuum-compatible reaction cell for model catalysis under atmospheric pressure flow conditions

Journal ArticleOpen Access

In: Review of Scientific Instruments, vol. 91, no. 12, pp. 125101, 2020.

Abstract | Links | BibTeX | Tags: P08, P10, pre-TACO

High-throughput study of the static dielectric constant at high temperatures in oxide and fluoride cubic perovskites

van Roekeghem, Ambroise; Carrete, Jesús; Curtarolo, Stefano; Mingo, Natalio

High-throughput study of the static dielectric constant at high temperatures in oxide and fluoride cubic perovskites

Journal Article

In: Physical Review Materials, vol. 4, no. 11, pp. 113804, 2020.

Abstract | Links | BibTeX | Tags: P09, pre-TACO

IrO2 Surface Complexions Identified through Machine Learning and Surface Investigations

Timmermann, Jakob; Kraushofer, Florian; Resch, Nikolaus; Li, Peigang; Wang, Yu; Mao, Zhiqiang; Riva, Michele; Lee, Yonghyuk; Staacke, Carsten; Schmid, Michael; Scheurer, Christoph; Parkinson, Gareth S.; Diebold, Ulrike; Reuter, Karsten

IrO2 Surface Complexions Identified through Machine Learning and Surface Investigations

Journal Article

In: Physical Review Letters, vol. 125, no. 20, pp. 206101, 2020.

Abstract | Links | BibTeX | Tags: P02, P04, pre-TACO

Ab initio structure and thermodynamics of the RPBE-D3 water/vapor interface by neural-network molecular dynamics

Wohlfahrt, Oliver; Dellago, Christoph; Sega, Marcello

Ab initio structure and thermodynamics of the RPBE-D3 water/vapor interface by neural-network molecular dynamics

Journal ArticleOpen Access

In: The Journal of Chemical Physics, vol. 153, no. 14, pp. 144710, 2020.

Abstract | Links | BibTeX | Tags: P12, pre-TACO

Atomically resolved surface phases of La0.8Sr0.2MnO3(110) thin films

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

Atomically resolved surface phases of La0.8Sr0.2MnO3(110) thin films

Journal ArticleOpen Access

In: Journal of Materials Chemistry A, vol. 8, no. 43, pp. 22947–22961, 2020.

Abstract | Links | BibTeX | Tags: P02, pre-TACO

43 entries « 2 of 5 »