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

DOI10.1016/J.CPC.2020.107206MaRDI QIDQ6044795zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Yuzhi Zhang, Haidi Wang, Weijie Chen, Jinzhe Zeng, Linfeng Zhang, Han Wang, Weinan E

Publication date 22 May 2023

Published in Computer Physics Communications (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1910.12690

zbMATH Keywords

concurrent learningdeep learningmany-body potential energy

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computational methods for problems pertaining to quantum theory (81-08) Quantum discord (81P43) Atomic physics (81V45) Molecular physics (81V55) Many-body theory; quantum Hall effect (81V70)

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.

Recommendations

• Deep Potential: A General Representation of a Many-Body Potential Energy Surface
• Molecular modeling by machine learning
• Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials
• Machine learning materials physics: integrable deep neural networks enable scale bridging by learning free energy functions
• The Gaussian Approximation Potential

Cites work

• Deep Potential: A General Representation of a Many-Body Potential Energy Surface
• Fast parallel algorithms for short-range molecular dynamics

Cited in

(5)

• Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
• Molecular modeling by machine learning
• PANNA: properties from artificial neural network architectures
• FLAME: a library of atomistic modeling environments
• Analysis and prediction of hematocrit in microvascular networks

This page was built for publication: DP-GEN: a concurrent learning platform for the generation of reliable deep learning based potential energy models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6044795)