DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models

TL;DR

DP-GEN is an open-source platform that automates the generation of reliable deep learning-based potential energy surface models through an iterative exploration, labeling, and training process, reducing human effort and computational costs.

Contribution

It introduces a novel, automated, and adaptable platform for generating accurate PES models using on-the-fly learning, integrating multiple software tools and supporting various computing environments.

Findings

Successfully generated a general-purpose PES model for Cu.

Demonstrated reduced human intervention and computational cost.

Validated the reliability of the generated PES models.

Abstract

In recent years, promising deep learning based interatomic potential energy surface (PES) models have been proposed that can potentially allow us to perform molecular dynamics simulations for large scale systems with quantum accuracy. However, making these models truly reliable and practically useful is still a very non-trivial task. A key component in this task is the generation of datasets used in model training. In this paper, we introduce the Deep Potential GENerator (DP-GEN), an open-source software platform that implements the recently proposed "on-the-fly" learning procedure [Phys. Rev. Materials 3, 023804] and is capable of generating uniformly accurate deep learning based PES models in a way that minimizes human intervention and the computational cost for data generation and model training. DP-GEN automatically and iteratively performs three steps: exploration, labeling, and training. It supports various popular packages for these three steps: LAMMPS for exploration, Quantum Espresso, VASP, CP2K, etc. for labeling, and DeePMD-kit for training. It also allows automatic job submission and result collection on different types of machines, such as high performance clusters and cloud machines, and is adaptive to different job management tools, including Slurm, PBS, and LSF. As a concrete example, we illustrate the details of the process for generating a general-purpose PES model for Cu using DP-GEN.