This project is about Density Functional Theory (DFT) and Machine Learning applied to Physical Chemistry, and it is part of my Postdoc research at Vanderbilt University. The title of the publication is:
Published on Theoretical Chemistry Accounts, part of the collection Machine Learning meets Quantum Chemistry Now available: https://link.springer.com/article/10.1007/s00214-024-03124-x
The prediction of hydrogen adsorption energies on complex oxides by integrating DFT calculations and Machine Learning is considered. In particular, 14 descriptors for electronic and geometric properties evaluation are adapted within a 336 hydrogen adsorption energy dataset created. Supervised learning techniques were explored to establish an accurate predictive model. With the Deep Neural Network results, a MAE of about 0.06 eV is achieved. This research highlights the synergistic potential of DFT and Machine Learning for accelerating the exploration of materials for catalysis, with a significance to assisting in the understanding of structure-reactivity relationship of high-entropy oxides.
Description: Predicting hydrogen adsorption energies on rocksalt complex oxides combining DFT calculations and machine learning.
Tools & Techniques: Python, pandas, scikit-learn, tensorflow, keras, Linear Regression,
Random Forest, Neural networks, Deep Learning, data visualization
Links: GitHub Repository
- Python 3.8.3
- TensorFlow 2.10.0
- Pandas 1.0.5
- Numpy 1.23.4
- Scikit-learn 1.3.2
- Keras 2.10.0
The full dataset was obtained from DFT calculations. (See Data.xlsx)
This repository is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. (See the LICENSE file).