The development of low-cost and highly-efficient pathways to produce renewable energy resources has been one of the top priorities in the science community. To that end, the holistic evaluation and the breathtaking success of MXenes have gained intense momentum by unlocking several new directions toward its usage in catalysis due to their evolutionary hallmark properties. However, the large variety of chemical compositions makes it highly difficult to screen appropriate materials. Hence, it is an urgent need to discover properties that provide information about the catalytic activity at a lower computational cost, particularly to screen over a pool of chemically related family of materials. With this aim, we establish a robust and more broadly applicable multistep workflow from the toolbox of supervised machine learning (ML) algorithms to construct well-trained data-driven models for predicting the hydrogen evolution reaction (HER) activity over 4,500
MXenes2Code.ipynb
We provide a step-wise procedure to predict the Gibbs Free Energy (target property) of the hydrogen adsorbed MXenes. The list of all the features are available in dataset.csv file and the DFT calculated Gibbs Free Energy of 1,125 MXenes are given in deltaG_H.csv, which are used in training the model.
MXenes2Model.zip
The best models (final RFR and GBR models) can be found in the zip folder, that can be further used for prediction of
Code4Plots.ipynb
Code for designing all the plots are provided here.
Dependencies
The following python libraries have been used in the current work:
- Pandas
- Scikit-learn
- Matplotlib
- Seaborn
- Re
- Joblib
B. Moses Abraham, Priyanka Sinha, Prosun Halder, Jayant K. Singh
Contact Details
Email address: jayantks@iitk.ac.in