Automated Discovery and Construction of Surface Phase Diagrams Using Machine Learning.

Surface phase diagrams are necessary for understanding surface chemistry in electrochemical catalysis, where a range of adsorbates and coverages exist at varying applied potentials. These diagrams are typically constructed using intuition, which risks missing complex coverages and configurations at potentials of interest. More accurate cluster expansion methods are often difficult to implement quickly for new surfaces. We adopt a machine learning approach to rectify both issues. Using a Gaussian process regression model, the free energy of all possible adsorbate coverages for surfaces is predicted for a finite number of adsorption sites. Our result demonstrates a rational, simple, and systematic approach for generating accurate free-energy diagrams with reduced computational resources. The Pourbaix diagram for the IrO2(110) surface (with nine coverages from fully hydrogenated to fully oxygenated surfaces) is reconstructed using just 20 electronic structure relaxations, compared to approximately 90 using typical search methods. Similar efficiency is demonstrated for the MoS2 surface.

[1]  Anton Van der Ven,et al.  Phase diagram of oxygen adsorbed on platinum (111) by first-principles investigation , 2004 .

[2]  Matthias Scheffler,et al.  Alloy surface segregation in reactive environments: First-principles atomistic thermodynamics study of Ag3Pd(111) in oxygen atmospheres , 2008, 0801.1144.

[3]  S. Müller,et al.  Adsorbate cluster expansion for an arbitrary number of inequivalent sites , 2008 .

[4]  Thomas Bligaard,et al.  Density functionals for surface science: Exchange-correlation model development with Bayesian error estimation , 2012 .

[5]  Stefano de Gironcoli,et al.  QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials , 2009, Journal of physics. Condensed matter : an Institute of Physics journal.

[6]  Jens K Nørskov,et al.  Surface Pourbaix diagrams and oxygen reduction activity of Pt, Ag and Ni(111) surfaces studied by DFT. , 2008, Physical chemistry chemical physics : PCCP.

[7]  Charlie Tsai,et al.  Active edge sites in MoSe2 and WSe2 catalysts for the hydrogen evolution reaction: a density functional study. , 2014, Physical chemistry chemical physics : PCCP.

[8]  Charlie Tsai,et al.  Tuning the MoS₂ edge-site activity for hydrogen evolution via support interactions. , 2014, Nano letters.

[9]  S. Goedecker Minima hopping: an efficient search method for the global minimum of the potential energy surface of complex molecular systems. , 2004, The Journal of chemical physics.

[10]  Karsten W. Jacobsen,et al.  An object-oriented scripting interface to a legacy electronic structure code , 2002, Comput. Sci. Eng..