Interfacial engineering and solar to hydrogen prediction in layer ordered, mono and double metal MXenes: a pure machine-learning framework

This folder contains information for generating machine learning pipeline to predict the MXenes structure by using inverse design. All the machine learning pipeline was executed using different Python Libraries i.e. pymatgen, Scikit learn, XGBoost, matplot etc. on open source Jupyter Notebook [5] and same was used for plotting the figures used in the manuscript. The authentic DFT data of more than 4000 2D functionalized MXenes for their thermodynamic, structural and electronic properties was taken from open source Ontiveros databases [1-4]. The executed Python script for machine learning and all the codes are available in the folder .ipynb_checkpoints within the supporting information zip file titled as Photocatalysis.zipThe intermediate csv files generated during the course of this study are also included in the zip folder.The generated images with their Python codes are also available in the zip folder. References: 1. Ontiveros, D., et al., MXgap: A MXene Learning Tool for Bandgap Prediction. ACS Catal, 2025. 15(16): p. 14403-14413. 2. Ontiveros, D., et al., Tuning MXenes Towards Their Use in Photocatalytic Water Splitting. ENERGY & ENVIRONMENTAL MATERIALS, 2024. 7(6): p. e12774. 3. Ontiveros, D., F. Viñes, and C. Sousa, Bandgap engineering of MXene compounds for water splitting. Journal of Materials Chemistry A, 2023. 11(25): p. 13754-13764. 4. Ontiveros, D., F. Viñes, and C. Sousa, Exploring the photoactive properties of promising MXenes for water splitting. Journal of Materials Chemistry A, 2024. 13: p. 3302-3316. 5. Granger, B.E. and F. Pérez, Jupyter: Thinking and Storytelling With Code and Data. Computing in Science & Engineering, 2021. 23(2): p. 7-14.