High-throughput screening of bimetallic catalysts enabled by machine learning

被引:283
作者
Li, Zheng [1 ]
Wang, Siwen [1 ]
Chin, Wei Shan [1 ]
Achenie, Luke E. [1 ]
Xin, Hongliang [1 ]
机构
[1] Virginia Tech, Dept Chem Engn, 635 Prices Fork Rd, Blacksburg, VA 24061 USA
基金
美国国家科学基金会;
关键词
OXYGEN REDUCTION; TRANSITION-METALS; SCALING RELATIONSHIPS; METHANOL; OXIDATION; REACTIVITY; CHEMISORPTION; ADSORPTION; PLATINUM; CO;
D O I
10.1039/c7ta01812f
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
We present a holistic machine-learning framework for rapid screening of bimetallic catalysts with the aid of the descriptor-based kinetic analysis. A catalyst database, which contains the adsorption energies of *CO and *OH on {111}-terminated model alloy surfaces and fingerprint features of active sites from density functional theory calculations with the semi-local generalized gradient approximation (GGA), is established and used in optimizing the structural and weight parameters of artificial neural networks. The fingerprint descriptors, rooted at the d-band chemisorption theory and its recent developments, include the sp-band and d-band characteristics of an adsorption site together with tabulated properties of host-metal atoms. Using methanol electro-oxidation as the model reaction, the machine-learning model trained with the existing dataset of similar to 1000 idealized alloy surfaces can capture complex, non-linear adsorbate/metal interactions with the RMSE similar to 0.2 eV and shows predictive power in exploring the immense chemical space of bimetallic catalysts. Feature importance analysis sheds light on the underlying factors that govern the adsorbate/metal interactions and provides the physical origin of bimetallics in breaking energy-scaling constraints of *CO and *OH, the two most commonly used reactivity descriptors in heterogeneous catalysis.
引用
收藏
页码:24131 / 24138
页数:8
相关论文
共 59 条
  • [1] Scaling properties of adsorption energies for hydrogen-containing molecules on transition-metal surfaces
    Abild-Pedersen, F.
    Greeley, J.
    Studt, F.
    Rossmeisl, J.
    Munter, T. R.
    Moses, P. G.
    Skulason, E.
    Bligaard, T.
    Norskov, J. K.
    [J]. PHYSICAL REVIEW LETTERS, 2007, 99 (01)
  • [2] Abu-Mostafa, 2012, Learning_from_data
  • [3] Informatics guided discovery of surface structure-chemistry relationships in catalytic nanoparticles
    Andriotis, Antonis N.
    Mpourmpakis, Giannis
    Broderick, Scott
    Rajan, Krishna
    Datta, Somnath
    Sunkara, Mahendra
    Menon, Madhu
    [J]. JOURNAL OF CHEMICAL PHYSICS, 2014, 140 (09)
  • [4] [Anonymous], 2009, ELECTROCATALYSIS DIR
  • [5] Electrocatalytic oxidation of methanol on the nickel-cobalt modified glassy carbon electrode in alkaline medium
    Asgari, Mehdi
    Maragheh, Mohammad Ghannadi
    Davarkhah, Reza
    Lohrasbi, Elaheh
    Golikand, Ahmad Nozad
    [J]. ELECTROCHIMICA ACTA, 2012, 59 : 284 - 289
  • [6] MECHANISM OF ELECTRO-OXIDATION OF METHANOL ON PLATINUM ELECTRODE
    BAGOTZKY, VS
    VASSILYEW, YB
    [J]. ELECTROCHIMICA ACTA, 1967, 12 (09) : 1323 - +
  • [7] The Bronsted-Evans-Polanyi relation and the volcano curve in heterogeneous catalysis
    Bligaard, T
    Norskov, JK
    Dahl, S
    Matthiesen, J
    Christensen, CH
    Sehested, J
    [J]. JOURNAL OF CATALYSIS, 2004, 224 (01) : 206 - 217
  • [8] Linear scaling relationships and volcano plots in homogeneous catalysis - revisiting the Suzuki reaction
    Busch, Michael
    Wodrich, Matthew D.
    Corminboeuf, Clemence
    [J]. CHEMICAL SCIENCE, 2015, 6 (12) : 6754 - 6761
  • [9] Physical and Chemical Nature of the Scaling Relations between Adsorption Energies of Atoms on Metal Surfaces
    Calle-Vallejo, F.
    Martinez, J. I.
    Garcia-Lastra, J. M.
    Rossmeisl, J.
    Koper, M. T. M.
    [J]. PHYSICAL REVIEW LETTERS, 2012, 108 (11)
  • [10] Accelerating the search for global minima on potential energy surfaces using machine learning
    Carr, S. F.
    Garnett, R.
    Lo, C. S.
    [J]. JOURNAL OF CHEMICAL PHYSICS, 2016, 145 (15)