Development of generalized potential-energy surfaces using many-body expansions, neural networks, and moiety energy approximations

Abstract

A general method for the development of potential-energy hypersurfaces is presented. The method combines a many-body expansion to represent the potential-energy surface with two-layer neural networks (NN) for each M-body term in the summations. The total number of NNs required is significantly reduced by employing a moiety energy approximation. An algorithm is presented that efficiently adjusts all the coupled NN parameters to the database for the surface. Application of the method to four different systems of increasing complexity shows that the fitting accuracy of the method is good to excellent. For some cases, it exceeds that available by other methods currently in literature. The method is illustrated by fitting large databases of ab initio energies for Si(n) (n=3,4,...,7) clusters obtained from density functional theory calculations and for vinyl bromide (C(2)H(3)Br) and all products for dissociation into six open reaction channels (12 if the reverse reactions are counted as separate open channels) that include C-H and C-Br bond scissions, three-center HBr dissociation, and three-center H(2) dissociation. The vinyl bromide database comprises the ab initio energies of 71 969 configurations computed at MP4(SDQ) level with a 6-31G(d,p) basis set for the carbon and hydrogen atoms and Huzinaga's (4333/433/4) basis set augmented with split outer s and p orbitals (43321/4321/4) and a polarization f orbital with an exponent of 0.5 for the bromine atom. It is found that an expansion truncated after the three-body terms is sufficient to fit the Si(5) system with a mean absolute testing set error of 5.693x10(-4) eV. Expansions truncated after the four-body terms for Si(n) (n=3,4,5) and Si(n) (n=3,4,...,7) provide fits whose mean absolute testing set errors are 0.0056 and 0.0212 eV, respectively. For vinyl bromide, a many-body expansion truncated after the four-body terms provides fitting accuracy with mean absolute testing set errors that range between 0.0782 and 0.0808 eV. These errors correspond to mean percent errors that fall in the range 0.98%-1.01%. Our best result using the present method truncated after the four-body summation with 16 NNs yields a testing set error that is 20.3% higher than that obtained using a 15-dimensional (15-140-1) NN to fit the vinyl bromide database. This appears to be the price of the added simplicity of the many-body expansion procedure.

High-dimensional neural network potentials for metal surfaces: A prototype study for copper

“…NNs of this type can be used directly to construct lowdimensional PESs of small molecules, and a number of examples can be found in the literature. [28][29][30][31][32][33][34] Further, they have also been applied successfully to study the adsorption of small molecules at metal surfaces. [35][36][37][38][39][40][41][42][43] Here, the frozen surface approximation has to be applied to reduce the dimensionality to a tractable size, and only the molecular degrees of freedom have been taken into account explicitly.…”

“…32,34,45 These approaches yield very accurate potentials, which can be systematically improved by using higher order terms and the corresponding NNs. Still, as the number of NNs grows rapidly with system size, these methods are computationally more demanding than standard NN potentials.…”

Molecular dynamics investigations of chlorine peroxide dissociation on a neural network ab initio potential energy surface

“…The PES construction requires an efficient sampling procedure [55][56][57]65] to sufficiently select data points from the multi-dimensional hyperspace. A particular construction of the NN PES perhaps requires more configurations to be selected than the other PES fitting methods.…”

Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations

“…Therefore, more ''systematic approaches'' have been developed, in which the emphasis is put on a rigorous expansion of the potential-energy in the spirit of a many-body expansion. NN potentials of this type have been proposed by Manzhos and Carrington,29,30 and also by Raff et al, 31 and involve a large number of individual NNs making this method accurate but computationally more demanding for large systems.…”