Search

A trivial flaw in the utilization of artificial neural networks in interpolating chemical potential energy surfaces (PES) whose descriptors are Cartesian coordinates is their dependence on simple translations and rotations of the molecule under consideration. A different set of descriptors can be chosen to circumvent this problem, internuclear distances, inverse internuclear distances or z‐matrix coordinates are three such descriptors. The objective is to use an interpolated PES in instanton rate constant calculations, hence information on the energy, gradient, and Hessian is required at coordinates in the vicinity of the tunneling path. Instanton theory relies on smoothly fitted Hessians, therefore we use energy, gradients, and Hessians in the training procedure. A major challenge is presented in the proper back‐transformation of the output gradients and Hessians from internal coordinates to Cartesian coordinates. We perform comparisons between our method, a previous approach and on‐the‐fly rate constant calcuations on the hydrogen abstraction from methanol and on the hydrogen addition to isocyanic acid. © 2018Wiley Periodicals, Inc. The challenge of utilizing instanton theory on interpolated potential energy surfaces, trained using a deep neural network, where energies, gradients and Hessians are required, in coordinates invariant to rotational and translational degrees of freedom, has been examined in this contribution. One of the studied reactions, shows good agreement both with existing neural network based approaches and with on‐the‐fly rate calculations based on a UCCSD(T)‐pVTZ‐F12 potential energy surface. [ABSTRACT FROM AUTHOR]