The training dataset, prediction dataset and code to reproduce the results of HER activity prediction for alloy nanoparticle

# HER activity prediction for alloy nanoparticle<br>The training dataset, prediction dataset and code to reproduce the results of HER activity prediction. <br><br>Note 1: Training procedure for both nanoparticle's stability and HER activity prediction was followed the instruction that described in detail in the paper.<br> "The MLIP package: moment tensor potentials with MPI and active learning". DOI 10.1088/2632-2153/abc9fe.<br> After training process for nanoparticle's stability prediction, trained MTP_stability can be used to predict energy for nanoparticle.<br> After training process for HER activity prediction, trained MTP_HER can be used to predict energy for H*_nanoparticle and nanoparticle. <br> The procedure to predict energy was described in detail in the MLIP package.<br><br>Note 2: The generation of bulk crystal structure was performed based on the cluster approach to statistical mechanics (CASM) package.<br> "CASM — A software package for first-principles based study of multicomponent crystalline solids package. DOI 10.1016/j.commatsci.2022.111897<br><br>There are 3 directories: Alloy nanoparticle catalytic activity prediction, Alloy nanoparticle stability prediction and Scripts. <br><br>1. The Scripts directory include the code to generate nanoparticle (NP) with diverse morphology and diameter, the code to generate training dataset. <br> - Gen_Solid_Solution_NP: generate the ordered solid solution nanoparticle with desired diameter from bulk structure.<br> - Gen_Core_Shell_NP: generate the core-shell nanoparticle by keeping the same the number of composition and atoms in solid solution nanoparticle<br> - Gen_Disordered_NP: generate the disordered nanoparticle.<br> - Convert_cif_cfg: converting the cif to cfg for further prediction using MLIP package.<br> - Convexhull_plot_NP: ploting convexhull based on the total energy prediction from MLIP package.<br> - Gen_surface_train: generate surface structure to construct necessary training dataset for nanoparticle's stability prediction.<br> - Gen_defective_surface_train: generate defective surface structure from surface structures generated by Gen_surface_train.py.<br> - Gen_H_adsorption_events: binding Hydrogen on the all possible active sites on surface structure that generated from Gen_surface_train.py and Gen_defective_surface_train.py<br><br>2. The Alloy nanoparticle stability prediction directory include the dataset to reproduce the results of nanoparticle's stability prediction:<br><br> - The validation data directory include the data to reproduce the parity plot for both force and energy.<br> - Before DFT optimization: include .cif files of structures of both core shell and solid solution NP in validation dataset and INCAR file for VASP full optimization. <br> - After DFT optimization: include .cif files of full optimization structures.<br> - Validation results: include .cfg files with energy and force predicted from MLIP package of structures in Before DFT optimization directory. Trained stability potential (MTP_stability) include the trained potential that can be used directly to predict energy of unrelaxed NP.<br> - Energy_Force_validation: CS_F and SS_F directories include the force for each NP in validation dataset.<br> E_valid.csv lists the energy/ atom (eV/atom) predicted from MLIP package and DFT full optimization of each NP in validation dataset.<br> F_valid.csv lists the force (eV/Angstrong) predicted from MLIP package and DFT full optimization of each NP in validation dataset.<br> <br> - Hyperparameter optimization directory include the data to reproduce the hyperparameter optimization selection.<br> - lev_max (potential compolexity): the .mtp is the potential used to predict energy and force of corresponding lev_max.<br> The prediction results include the .cfg file (comprising energy and force predicted by MLIP package) and corresponding force (.csv file).<br> - r cutoff (cutoff radius): the .mtp is the potential used to predict energy and force of corresponding r_cutoff.<br> The prediction results include the .cfg file (comprising energy and force predicted by MLIP package) and corresponding force (.csv file).<br> - weight_ratio: the .mtp is the potential used to predict energy and force of corresponding energy-to-force-weight.<br> The prediction results include the .cfg file (comprising energy and force predicted by MLIP package) and corresponding force (.csv file).<br><br> - Stable nanoparticle directory include the most stable nanoparticle found in the convex hulll of PtAu, PtNi and PtCo nanoparticle with diameter up to 4nm.<br><br> - The prediction directory include the prediction data (test dataset) for nanoparticle stability prediction.<br> The predictions were performed for PtNi, PtAu (FCC-FCC) and PtCo (FCC-HCP).<br> The generation of training dataset and prediction dataset for the nanoparticle in same class is similar. - PtNi: include Prediction dataset, Prediction results, Training dataset and Trained potential.<br> - Prediction dataset: .cif file of nanoparticle that need to predict energy.<br> - Prediction results: .cfg file of nanoparticle that predicted by MLIP package.<br> - Training dataset: bulk and surface structure used to trained MLIP.<br> - PtAu, PtCo: the directory structure is the same as PtNi.<br><br>3. Alloy nanoparticle catalytic activity prediction directory include the dataset to reproduce the results of HER activity prediction<br><br> - Validation directory comprise the validation for various nanoparticle (PtNi, PtAu, PtCo) with different morphologies (coreshell, solid solution and disorder nanoparticle).<br> - PtNi: include various nanoparticle for validation. The validation of each nanoparticle divide into 3 directories:<br> - Trained MTP_HER: already trained MTP that can be used to predict energy of H*_nanoparticle and nanoparticle.<br> - Validation dataset: unrelaxed .cif files of H adsorption events on surface of nanoparticle and corresponding relaxed .cif files.<br> The optimization was performed using DFT method by VASP.5.4.4 (the INCAR file for VASP also provided)<br> - Validation results: .cfg files (structure coordination and energy) predicted from trained MTP_HER for structures in Validation dataset. <br> - PtAu, PtCo: the directory structure is the same as PtNi.<br><br> - Prediction directory: include the HER prediction results for all stable nanoparticle listed in Stable nanoparticle directory.<br> - PtNi: include the HER prediction results for stable nanoparticle at 2,3 and 4 nm. <br> HER prediction for each nanoparticle was divide into 4 directories:<br> - Training dataset: training dataset used as input for MTP training process.<br> - Trained MTP_HER: already trained MTP that can be used to predict energy of H*_nanoparticle and nanoparticle.<br> - Prediction dataset: .cif files of all possible H adsorption events on surface of nanoparticle.<br> - Prediction results: .cfg files (structure coordination and energy) predicted from trained MTP_HER for structures in Prediction dataset. <br>