On-the-Fly Machine Learning of Atomic Potential in Density Functional Theory Structure Optimization.

Machine learning (ML) is used to derive local stability information for density functional theory calculations of systems in relation to the recently discovered SnO_{2}(110)-(4×1) reconstruction. The ML model is trained on (structure, total energy) relations collected during global minimum energy search runs with an evolutionary algorithm (EA). While being built, the ML model is used to guide the EA, thereby speeding up the overall rate by which the EA succeeds. Inspection of the local atomic potentials emerging from the model further shows chemically intuitive patterns.

[1]  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.

[2]  Zhenwei Li,et al.  Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces. , 2015, Physical review letters.

[3]  A. Oganov,et al.  Crystal structure prediction using ab initio evolutionary techniques: principles and applications. , 2006, The Journal of chemical physics.

[4]  R. Kondor,et al.  On representing chemical environments , 2012, 1209.3140.

[5]  M. Lazzeri,et al.  Stress-driven reconstruction of an oxide surface: the anatase TiO(2)(001)-(1 x 4) surface. , 2001, Physical review letters.

[6]  M Schmid,et al.  Structure of Ag(111)-p(4 x 4)-O: no silver oxide. , 2006, Physical review letters.

[7]  Rampi Ramprasad,et al.  Adaptive machine learning framework to accelerate ab initio molecular dynamics , 2015 .

[8]  Chris J Pickard,et al.  Ab initio random structure searching , 2011, Journal of physics. Condensed matter : an Institute of Physics journal.

[9]  Alexandre Tkatchenko,et al.  Quantum-chemical insights from deep tensor neural networks , 2016, Nature Communications.

[10]  A. Laio,et al.  Escaping free-energy minima , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Klaus-Robert Müller,et al.  Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies. , 2013, Journal of chemical theory and computation.

[12]  A. Gross,et al.  Representing high-dimensional potential-energy surfaces for reactions at surfaces by neural networks , 2004 .

[13]  A Michaelides,et al.  Revisiting the structure of the p(4 x 4) surface oxide on Ag(111). , 2006, Physical review letters.

[14]  John E. Herr,et al.  Intrinsic Bond Energies from a Bonds-in-Molecules Neural Network. , 2017, The journal of physical chemistry letters.

[15]  Georg Kresse,et al.  Structure of the Ultrathin Aluminum Oxide Film on NiAl(110) , 2005, Science.

[16]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.

[17]  George E. Dahl,et al.  Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error. , 2017, Journal of chemical theory and computation.

[18]  Anastassia N Alexandrova,et al.  Search for the Lin(0/+1/-1) (n = 5-7) Lowest-Energy Structures Using the ab Initio Gradient Embedded Genetic Algorithm (GEGA). Elucidation of the Chemical Bonding in the Lithium Clusters. , 2005, Journal of chemical theory and computation.

[19]  Chris J. Pickard,et al.  Predicting interface structures: From SrTiO 3 to graphene , 2014, 1407.2153.

[20]  O. A. von Lilienfeld,et al.  Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity. , 2016, The Journal of chemical physics.

[21]  Bjørk Hammer,et al.  Combining Evolutionary Algorithms with Clustering toward Rational Global Structure Optimization at the Atomic Scale. , 2017, Journal of chemical theory and computation.

[22]  Mario Valle,et al.  How to quantify energy landscapes of solids. , 2009, The Journal of chemical physics.

[23]  A. Atrei,et al.  The SnO2(110)(4 × 1) structure determined by LEED intensity analysis , 2001 .

[24]  Annabella Selloni,et al.  Stress-Driven Reconstruction of an Oxide Surface , 2001 .

[25]  Matthias Scheffler,et al.  Stability and metastability of clusters in a reactive atmosphere: theoretical evidence for unexpected stoichiometries of MgMOx. , 2013, Physical review letters.

[26]  Alireza Khorshidi,et al.  Amp: A modular approach to machine learning in atomistic simulations , 2016, Comput. Phys. Commun..

[27]  Claire S. Adjiman,et al.  Report on the sixth blind test of organic crystal structure prediction methods , 2016, Acta crystallographica Section B, Structural science, crystal engineering and materials.

[28]  J. Doye,et al.  Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms , 1997, cond-mat/9803344.

[29]  K. Müller,et al.  Fast and accurate modeling of molecular atomization energies with machine learning. , 2011, Physical review letters.

[30]  Ho,et al.  Molecular geometry optimization with a genetic algorithm. , 1995, Physical review letters.

[31]  B. Hammer,et al.  Steps on rutile TiO 2 (110): Active sites for water and methanol dissociation , 2011, 1111.0428.

[32]  U. Diebold,et al.  Surface morphologies of SnO2(1 1 0) , 2003 .

[33]  Chu Zhang,et al.  Structure of the SnO_{2}(110)-(4×1) Surface. , 2017, Physical review letters.

[34]  K. Jacobsen,et al.  Real-space grid implementation of the projector augmented wave method , 2004, cond-mat/0411218.

[35]  Tarak K Patra,et al.  Neural-Network-Biased Genetic Algorithms for Materials Design: Evolutionary Algorithms That Learn. , 2017, ACS combinatorial science.

[36]  M. Rupp,et al.  Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties , 2013, 1307.2918.

[37]  Bjørk Hammer,et al.  Systematic study of Au6 to Au12 gold clusters on MgO(100) F centers using density-functional theory. , 2012, Physical review letters.

[38]  U. Starke,et al.  NOVEL RECONSTRUCTION MECHANISM FOR DANGLING-BOND MINIMIZATION : COMBINED METHOD SURFACE STRUCTURE DETERMINATION OF SIC(111)-(3 X 3) , 1998 .

[39]  K. Müller,et al.  Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space , 2015, The journal of physical chemistry letters.

[40]  R. Johnston.  Evolving better nanoparticles: Genetic algorithms for optimising cluster geometries , 2003 .

[41]  Bjørk Hammer,et al.  A genetic algorithm for first principles global structure optimization of supported nano structures. , 2014, The Journal of chemical physics.

[42]  Francisco B. Pereira,et al.  An evolutionary algorithm for global minimum search of binary atomic clusters , 2010 .

[43]  Dmitry Yu. Zubarev,et al.  Global minimum structure searches via particle swarm optimization , 2007, J. Comput. Chem..

[44]  B. Hartke.  Global geometry optimization of clusters using genetic algorithms , 1993 .