GPU-Accelerated Neural Network Potential Energy Surfaces for Diffusion Monte Carlo

Abstract

Diffusion Monte Carlo (DMC) provides a powerful method for understanding the vibrational landscape of molecules that are not well-described by conventional methods. The most computationally demanding step of these calculations is the evaluation of the potential energy. In this work, a general approach is developed in which a neural network potential energy surface is trained by using data generated from a small-scale DMC calculation. Once trained, the neural network can be evaluated by using highly parallelizable calls to a graphics processing unit (GPU). The power of this approach is demonstrated for DMC simulations on H2O, CH5 +, and (H2O)2. The need to include permutation symmetry in the neural network potentials is explored and incorporated into the molecular descriptors of CH5 + and (H2O)2. It is shown that the zero-point energies and wave functions obtained by using the neural network potentials are nearly identical to the results obtained when using the potential energy surfaces that were used to train the neural networks at a substantial savings in the computational requirements of the simulations.

Transfer learned potential energy surfaces: accurate anharmonic vibrational dynamics and dissociation energies for the formic acid monomer and dimer

“…The use of GPUs for the evaluation of PhysNet speeds up the calculations as they can be performed in a highly parallel manner. 92 Here, all DMC calculations were performed on a GeForce RTX 2080Ti GPU with 12 Gb of RAM. Each DMC simulation for FAM (FAD) takes 8.7 (23.7) h on average.…”

Using Diffusion Monte Carlo Wave Functions to Analyze the Vibrational Spectra of H7O3+ and H9O4+

“…Furthermore, the method relies on the ability to calculate the potential energy and dipole functions with sufficient accuracy for spectral evaluation and the ability to construct a set of internal coordinates as a basis for these calculations. While the availability of a potential often limits the types of systems that can be explored with the GSPA approach, we have recently expanded our DMC calculations to allow us to utilize direct evaluation of electronic energies …”

“…While the availability of a potential often limits the types of systems that can be explored with the GSPA approach, we have recently expanded our DMC calculations to allow us to utilize direct evaluation of electronic energies. 48 ■ ASSOCIATED CONTENT * sı Supporting Information…”

Transfer Learned Potential Energy Surfaces: Accurate Anharmonic Vibrational Dynamics and Dissociation Energies for the Formic Acid Monomer and Dimer

“…The use of GPUs for the evaluation of PhysNet speeds up the calculations as they can be performed in a highly parallel manner. 82 Here, all DMC calculations were performed on a GeForce RTX 2080Ti GPU with 12 Gb of RAM. Each DMC simulation for FAM (FAD) takes 8.7 (23.7) h on average.…”