English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

In recent years, promising deep learning based interatomic potential energysurface (PES) models have been proposed that can potentially allow us toperform molecular dynamics simulations for large scale systems with quantumaccuracy. However, making these models truly reliable and practically useful isstill a very non-trivial task. A key component in this task is the generationof datasets used in model training. In this paper, we introduce the DeepPotential GENerator (DP-GEN), an open-source software platform that implementsthe recently proposed "on-the-fly" learning procedure [Phys. Rev. Materials 3,023804] and is capable of generating uniformly accurate deep learning based PESmodels in a way that minimizes human intervention and the computational costfor data generation and model training. DP-GEN automatically and iterativelyperforms three steps: exploration, labeling, and training. It supports variouspopular packages for these three steps: LAMMPS for exploration, QuantumEspresso, VASP, CP2K, etc. for labeling, and DeePMD-kit for training. It alsoallows automatic job submission and result collection on different types ofmachines, such as high performance clusters and cloud machines, and is adaptiveto different job management tools, including Slurm, PBS, and LSF. As a concreteexample, we illustrate the details of the process for generating ageneral-purpose PES model for Cu using DP-GEN.

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