jz9b02838_si_001.pdf (1.4 MB)
Toward the Exact Exchange–Correlation Potential: A Three-Dimensional Convolutional Neural Network Construct
journal contribution
posted on 2019-11-11, 18:39 authored by Yi Zhou, Jiang Wu, Shuguang Chen, GuanHua ChenA deep neural network
is constructed to yield in principle exact
exchange–correlation potential. It requires merely the electron
densities of small molecules and ions and yet can determine the exchange–correlation
potentials of large molecules. We train and validate the neural network
based on the data for H2 and HeH+ and subsequently
determine the ground-state electron density of stretched HeH+, linear H3+, and H–He–He–H2+. Moreover, the deep neural network is proven to model the
van der Waals interaction by being trained and validated on a data
set containing He2. Comparisons to B3LYP are given to illustrate
the accuracy and transferability of the neural network.