REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems

TL;DR

REANN is a versatile, PyTorch-based deep learning package that accurately models energies, forces, and molecular properties across diverse atomistic systems, enabling scalable simulations and future method development.

Contribution

It introduces a general-purpose, multi-functional neural network package combining physical descriptors and message passing, with automated hyperparameter optimization and broad applicability.

Findings

Achieves state-of-the-art accuracy in energy and property predictions

Demonstrates high efficiency and scalability in molecular systems

Provides an interface for large-scale molecular dynamics simulations

Abstract

In this work, we present a general purpose deep neural network package for representing energies, forces, dipole moments, and polarizabilities of atomistic systems. This so-called recursively embedded atom neural network model takes both advantages of the physically inspired atomic descriptor based neural networks and the message-passing based neural networks. Implemented in the PyTorch framework, the training process is parallelized on both CPU and GPU with high efficiency and low memory, in which all hyperparameters can be optimized automatically. We demonstrate the state-of-the-art accuracy, high efficiency, scalability, and universality of this package by learning not only energies (with or without forces), but also dipole moment vectors and polarizability tensors, in various molecular, reactive, and periodic systems. An interface between a trained model and LAMMPs is provided for large scale molecular dynamics simulations. We hope that this open-source toolbox will allow future method development and applications of machine learned potential energy surfaces and quantum-chemical properties of molecules, reactions, and materials.