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

Revealing Li-ion Stage reaction in Graphite via Machine-Learning Interatomic Potential and Genetic AlgorithmFiles are composed of these directories:<b>DFT</b><b>GA-MLIP</b><b>DFT</b>This directory contains the structural models used for DFT calculations, provided in CIF format.<b>Ordering_model</b><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.<b>SOC100</b> : Contains structures with distinct space groups designed to vary the facing degree of Li ions.<b>Stacking_model</b>Contains the ground-state structural models for the stacking transition discussed in the manuscript.<b>Global-Lithiation</b> : CIF files representing the global lithiation model.<b>Local-Lithiation</b> : CIF files representing the local lithiation model.Includes sub-directories: soc100_fix , soc75_fix , soc50_fix<b>GA-MLIP</b>This directory includes the source code, input files, machine learning potential, and environment configurations required to reproduce the GA-MLIP simulation.<b>Root Files</b><b>run_pipeline.py</b> : The main execution script for running the GA-MLIP workflow.<b>input.cif</b> : The initial input structure file used for the simulation.<b>sevenet_model.pth</b> : The fine-tunned machine learning interatomic potential (SevenNet) model file used in this study.<b>GA-MLIP.yaml</b> : The Conda environment file included to ensure reproducibility of the computational environment.<b>Sub-directories</b><b>config</b>params.json : Manages simulation parameters, defining the hyperparameters and settings for the GA process.<b>operators</b>Contains scripts for genetic operators, including structure generation (random) and variation (mutation) algorithms.<b>src</b>Houses the main source code for each step of the genetic algorithm pipeline.<b>utility</b>A collection of utility scripts and helper functions required for code execution.<b>results</b><b>Best Structures</b> : Contains the final optimized structures (best CIFs) for each SOC level derived from the GA-MLIP simulations.