Machine-Learning Database for paper "Transport Properties of Liquid Hydrogen Using Deep Potential Molecular Dynamics"
Abstract
In the init/02.develop_data folder, VASP files are provided for configurations used to explore the phase space of liquid hydrogen potential. In the run folder, the following files are provided: - cp2k.inp: template file for DFT calculations by DP-GEN; - dpgen_nohup.sh: script for submitting DP-GEN iterative training tasks on a supercomputer; - frozen_model.pb: final potential obtained after 15 training iterations; - machine_slurm_cp2k.json: JSON file for configuring resources for DP-GEN to interface with CP2K, LAMMPS, etc.; - param_cp2k.json: the most important file for potential training, providing various key information for the training process.
Fields of Study & Subjects
Machine Learning in Materials Science
Advanced Chemical Physics Studies
High-pressure geophysics and materials
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 12 March 2026
- Language
- EN
- Document type
- Dataset