Representing molecule-surface interactions with symmetry-adapted neural networks.

The accurate description of molecule-surface interactions requires a detailed knowledge of the underlying potential-energy surface (PES). Recently, neural networks (NNs) have been shown to be an efficient technique to accurately interpolate the PES information provided for a set of molecular configurations, e.g., by first-principles calculations. Here, we further develop this approach by building the NN on a new type of symmetry functions, which allows to take the symmetry of the surface exactly into account. The accuracy and efficiency of such symmetry-adapted NNs is illustrated by the application to a six-dimensional PES describing the interaction of oxygen molecules with the Al(111) surface.

[1]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[2]  B. Delley.  An all‐electron numerical method for solving the local density functional for polyatomic molecules , 1990 .

[3]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[4]  Nielsen,et al.  Multidimensional effects in dissociative chemisorption: H2 on Cu and Ni surfaces. , 1992, Physical review. B, Condensed matter.

[5]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[6]  Thomas B. Blank,et al.  Adaptive, global, extended Kalman filters for training feedforward neural networks , 1994 .

[7]  J. G. Snijders,et al.  Performance of close-coupled wave packet methods for molecule-corrugated surface scattering , 1995 .

[8]  Steven D. Brown,et al.  Neural network models of potential energy surfaces , 1995 .

[9]  Six-dimensional quantum dynamics of adsorption and desorption of H2 at Pd(100): Steering and steric effects. , 1995, Physical review letters.

[10]  Mark N. Gibbs,et al.  Combining ab initio computations, neural networks, and diffusion Monte Carlo: An efficient method to treat weakly bound molecules , 1996 .

[11]  E. J. Baerends,et al.  An analytical six-dimensional potential energy surface for dissociation of molecular hydrogen on Cu(100) , 1996 .

[12]  Harold A. Scheraga,et al.  Description of the potential energy surface of the water dimer with an artificial neural network , 1997 .

[13]  J. J. Soares Neto,et al.  The fitting of potential energy surfaces using neural networks: Application to the study of vibrational levels of H3+ , 1998 .

[14]  Dmitrii E. Makarov,et al.  FITTING POTENTIAL-ENERGY SURFACES : A SEARCH IN THE FUNCTION SPACE BY DIRECTED GENETIC PROGRAMMING , 1998 .

[15]  Ab initio calculation of the potential energy surface for the dissociation of H_2 on the sulfur-covered Pd(100) surface , 1997, cond-mat/9711289.

[16]  Ab initio quantum and molecular dynamics of the dissociative adsorption of hydrogen on Pd(100) , 1997, cond-mat/9705102.

[17]  J. J. Soares Neto,et al.  The fitting of potential energy surfaces using neural networks. Application to the study of the photodissociation processes , 1998 .

[18]  Matthias Scheffler,et al.  Ab initio based tight-binding Hamiltonian for the dissociation of molecules at surfaces , 1999 .

[19]  J. Nørskov,et al.  Improved adsorption energetics within density-functional theory using revised Perdew-Burke-Ernzerhof functionals , 1999 .

[20]  Michael A. Collins,et al.  Learning to interpolate molecular potential energy surfaces with confidence: A Bayesian approach , 1999 .

[21]  W. Dong,et al.  Six-dimensional classical dynamics of H2 dissociative adsorption on Pd(111) , 2000 .

[22]  Georg Kresse,et al.  Dissociation and sticking of H 2 on the Ni(111), (100), and (110) substrate , 2000 .

[23]  B. Delley.  From molecules to solids with the DMol3 approach , 2000 .

[24]  W. Dong,et al.  Analysis of H2 dissociation dynamics on the Pd(111) surface , 2001 .

[25]  Michael A. Collins,et al.  Multi-dimensional potential energy surface determination by modified Shepard interpolation for a molecule–surface reaction: H2+Pt(111) , 2003 .

[26]  F. V. Prudente,et al.  The fitting of potential energy and transition moment functions using neural networks: transition probabilities in OH (A2Σ+→X2Π) , 2004 .

[27]  G. Kroes,et al.  Application of the modified Shepard interpolation method to the determination of the potential energy surface for a molecule-surface reaction: H2 + Pt(111). , 2004, The Journal of chemical physics.

[28]  J. Behler,et al.  Dissociation of oxygen molecules on the Al(111) surface , 2004 .

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

[30]  M. Hagan,et al.  Prediction of molecular-dynamics simulation results using feedforward neural networks: reaction of a C2 dimer with an activated diamond (100) surface. , 2005, The Journal of chemical physics.

[31]  R Komanduri,et al.  Ab initio potential-energy surfaces for complex, multichannel systems using modified novelty sampling and feedforward neural networks. , 2005, The Journal of chemical physics.

[32]  J. Behler,et al.  Dissociation of O2 at Al(111): the role of spin selection rules. , 2004, Physical Review Letters.

[33]  Ranga Komanduri,et al.  Molecular dynamics investigations of the dissociation of SiO2 on an ab initio potential energy surface obtained using neural network methods. , 2006, The Journal of chemical physics.

[34]  A. Gross,et al.  Descriptions of surface chemical reactions using a neural network representation of the potential-energy surface , 2006 .

[35]  Sergei Manzhos,et al.  A random-sampling high dimensional model representation neural network for building potential energy surfaces. , 2006, The Journal of chemical physics.

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

[37]  B. Delley,et al.  Nonadiabatic potential-energy surfaces by constrained density-functional theory , 2006, cond-mat/0605292.