Pairwise interactions for Potential energy surfaces and Atomic forces with Deep Neural network

TL;DR

This paper introduces a deep neural network model that captures pairwise atomic interactions and local structure features to accurately predict energies and forces in molecular dynamics, improving efficiency over traditional methods.

Contribution

The work presents a novel neural network architecture that incorporates pairwise interactions and Coulomb matrices, enhancing accuracy and transferability in atomic force and energy predictions.

Findings

High accuracy in predicting forces and energies for silicon systems

Improved transferability to larger atomic systems

Enhanced model performance by integrating pairwise and local structure features

Abstract

Molecular dynamics (MD) simulation, which is considered an important tool for studying physical and chemical processes at the atomic scale, requires accurate calculations of energies and forces. Although reliable energies and forces can be obtained by electronic structure calculations such as those based on density functional theory (DFT), this approach is computationally expensive. In this work, we propose a full-stack model using deep neural network (NN) to enhance the calculation of force and energy, in which the NN is designed to extract the embedding feature of pairwise interactions of an atom and its neighbors, which are aggregated to obtain its feature vector for predicting atomic force and potential energy. By designing the features of the pairwise interactions, we can control the performance of models and take into account the many-body effects and other physics of the atomic interactions. Moreover, we demonstrated that using the Coulomb matrix of the local structures in complement to the pairwise information, we can improve the prediction of force and energy for silicon systems and the transferability of our models is confirmed to larger systems, with high accuracy.