First-principles database driven computational neural network approach to the discovery of active ternary nanocatalysts for oxygen reduction reaction.

@article{Kang2018FirstprinciplesDD,
  title={First-principles database driven computational neural network approach to the discovery of active ternary nanocatalysts for oxygen reduction reaction.},
  author={Joonhee Kang and Seung Hyo Noh and Jeemin Hwang and Hoje Chun and Hansung Kim and Byungchan Han},
  journal={Physical chemistry chemical physics : PCCP},
  year={2018},
  volume={20 38},
  pages={
          24539-24544
        }
}
An elegant machine-learning-based algorithm was applied to study the thermo-electrochemical properties of ternary nanocatalysts for oxygen reduction reaction (ORR). High-dimensional neural network potentials (NNPs) for the interactions among the components were parameterized from big dataset established by first-principles density functional theory calculations. The NNPs were then incorporated with Monte Carlo (MC) and molecular dynamics (MD) simulations to identify not only active, but also… 
View on PubMed
rsc.org
12 Citations
Methods Citations
1

12 Citations

Citation Type

Citation Type

First-principle-data-integrated machine-learning approach for high-throughput searching of ternary electrocatalyst toward oxygen reduction reaction
First-principles based machine learning study of oxygen evolution reactions of perovskite oxides using a surface center-environment feature model
Multitribe evolutionary search for stable Cu-Pd-Ag nanoparticles using neural network models.
We present an approach based on two bio-inspired algorithms to accelerate the identification of nanoparticle ground states. We show that a symbiotic co-evolution of nanoclusters across a range of…
Molecular dynamics study on magnesium hydride nanoclusters with machine-learning interatomic potential
We introduce a machine-learning (ML) interatomic potential for Mg-H system based on Behler-Parrinello approach. In order to fit the complex bonding conditions in the cluster structure, we combine…
Progress in Computational and Machine-Learning Methods for Heterogeneous Small-Molecule Activation.
TLDR
The theory and methodologies for heterogeneous catalysis and their applications for small-molecule activation are reviewed and promising directions of the computational catalysis field for further outlooks are discussed, focusing on the challenges and opportunities for new methods.
First-principles computational approach for innovative design of highly functional electrocatalysts in fuel cells
Applying machine learning to boost the development of high-performance membrane electrode assembly for proton exchange membrane fuel cells
TLDR
A standard workflow consisting of four processing modules, starting with feature selection followed by decision modeling, regression modeling and extremum optimization is set up, which immediately inferred 13 optimal parameters based on existing conditions provided by users.
Structural search for stable Mg-Ca alloys accelerated with a neural network interatomic model.
TLDR
A neural network formalism with metaheuristic structural global search algorithms is combined to systematically screen the Mg-Ca binary system for new (meta)stable alloys to allow for an efficient exploration of the potential energy surface beyond the possibility of the traditional searches based on ab initio energy evaluations.
On machine learning force fields for metallic nanoparticles
TLDR
The most commonly used machine learning algorithms for force field generation are introduced, briefly outlining their structure and properties, and the core issue of training database selection is addressed, reporting methodologies both already used and yet unused in literature.
Machine learning for alloys
Alloy modelling has a history of machine-learning-like approaches, preceding the tide of data-science-inspired work. The dawn of computational databases has made the integration of analysis,…
...
1
2
...

References

SHOWING 1-10 OF 40 REFERENCES
First-principles computational study of highly stable and active ternary PtCuNi nanocatalyst for oxygen reduction reaction
Using density functional theory (DFT) calculations, we rationally designed metallic nanocatalysts with ternary transition metals for oxygen reduction reactions (ORRs) in fuel cell applications. We…
Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO2 Reduction
Bimetallic catalysts are promising for the most difficult thermal and electrochemical reactions, but modeling the many diverse active sites on polycrystalline samples is an open challenge. We present…
Understanding the composition and activity of electrocatalytic nanoalloys in aqueous solvents: a combination of DFT and accurate neural network potentials.
TLDR
A combination of first-principles computations and large-scale Monte-Carlo simulations with highly accurate neural network potentials are employed to study the equilibrium surface structure and composition of bimetallic Au/Cu nanoparticles (NPs), which have recently been of interest as stable and efficient CO2 reduction catalysts.
To address surface reaction network complexity using scaling relations machine learning and DFT calculations
TLDR
A framework for optimization under uncertainty for heterogeneous catalysis reaction networks using surrogate models that are trained on the fly to predict the most important reaction step to be calculated explicitly with computationally demanding electronic structure theory.
First-Principles Design of Graphene-Based Active Catalysts for Oxygen Reduction and Evolution Reactions in the Aprotic Li-O2 Battery.
Using first-principles density functional theory (DFT) calculations, we demonstrate that catalytic activities toward oxygen reduction and evolution reactions (ORR and OER) in a Li-O2 battery can be…
Towards a comprehensive understanding of FeCo coated with N-doped carbon as a stable bi-functional catalyst in acidic media
The identification and development of efficient catalysts made of non-precious materials for oxygen reduction reaction (ORR) are essential for the successful operation of a wide range of energy…
First-principles thermodynamic study of the electrochemical stability of Pt nanoparticles in fuel cell applications
Roles of Mo Surface Dopants in Enhancing the ORR Performance of Octahedral PtNi Nanoparticles.
TLDR
Electrochemistry, ex situ and in situ spectroscopic techniques, density functional theory calculations, and a newly developed kinetic Monte Carlo model show that Mo atoms are preferentially located on the vertex and edge sites of Mo-PtNi/C in the form of oxides, which are stable within the wide potential window of the electrochemical cycle.
Unveiling Hidden Catalysts for the Oxidative Coupling of Methane based on Combining Machine Learning with Literature Data
Catalysts for oxidative coupling of methane (OCM) are explored using data science and 1868 OCM catalysts from literature data. Machine learning reveals the descriptors responsible for determining the…
Changing the activity of electrocatalysts for oxygen reduction by tuning the surface electronic structure.
TLDR
Pt alloys involving 3d metals are better catalysts than Pt because the electronic structure of the Pt atoms in the surface of these alloys has been modified slightly, and it is shown that electrocatalysts can be designed on the basis of fundamental insight.
...
1
2
3
4
...