figshare
Browse

Revealing Li-ion Stage reaction in Graphite via Machine-Learning Interatomic Potential and Genetic Algorithm

Download (18.32 MB)
Version 2 2026-01-07, 09:30
Version 1 2025-12-12, 09:28
dataset
posted on 2026-01-07, 09:30 authored by Yong Hui Kim, Sang Uck Lee
<p dir="ltr">Revealing Li-ion Stage reaction in Graphite via Machine-Learning Interatomic Potential and Genetic Algorithm</p><p dir="ltr">Files are composed of these directories:</p><ul><li><b>DFT</b></li><li><b>GA-MLIP</b></li></ul><h4><b>DFT</b></h4><p dir="ltr">This directory contains the structural models used for DFT calculations, provided in CIF format.</p><ul><li><b>Ordering_model</b></li><li><ul><li><b>SOC25, </b><b>SOC</b><b>50, </b><b>SOC</b><b>75</b> : Contains structural models representing specific ordering types (Off-facing, Alternating, Facing) for each SOC level.</li><li><b>SOC100</b> : Contains structures with distinct space groups designed to vary the facing degree of Li ions.</li></ul></li><li><b>Stacking_model</b></li><li><ul><li>Contains the ground-state structural models for the stacking transition discussed in the manuscript.</li><li><b>Global-Lithiation</b> : CIF files representing the global lithiation model.</li><li><b>Local-Lithiation</b> : CIF files representing the local lithiation model.</li><li><ul><li>Includes sub-directories: soc100_fix , soc75_fix , soc50_fix</li></ul></li></ul></li></ul><h4><b>GA-MLIP</b></h4><p dir="ltr">This directory includes the source code, input files, machine learning potential, and environment configurations required to reproduce the GA-MLIP simulation.</p><ul><li><b>Root Files</b></li><li><ul><li><b>run_pipeline.py</b> : The main execution script for running the GA-MLIP workflow.</li><li><b>input.cif</b> : The initial input structure file used for the simulation.</li><li><b>sevenet_model.pth</b> : The fine-tunned machine learning interatomic potential (SevenNet) model file used in this study.</li><li><b>GA-MLIP.yaml</b> : The Conda environment file included to ensure reproducibility of the computational environment.</li></ul></li><li><b>Sub-directories</b></li><li><ul><li><b>config</b></li><li><ul><li>params.json : Manages simulation parameters, defining the hyperparameters and settings for the GA process.</li></ul></li><li><b>operators</b></li><li><ul><li>Contains scripts for genetic operators, including structure generation (random) and variation (mutation) algorithms.</li></ul></li><li><b>src</b></li><li><ul><li>Houses the main source code for each step of the genetic algorithm pipeline.</li></ul></li><li><b>utility</b></li><li><ul><li>A collection of utility scripts and helper functions required for code execution.</li></ul></li><li><b>results</b></li><li><ul><li><b>Best Structures</b> : Contains the final optimized structures (best CIFs) for each SOC level derived from the GA-MLIP simulations.</li></ul></li></ul></li></ul><p></p>

History

Related Materials

Usage metrics

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC