pySIPFENN MGF-PSU Workshop (Feb 2023)

This Jupyter notebook is a brief walkthrough covering core functionalities of the pySIPFENN or py(Structure-Informed Prediction of Formation Energy using Neural Networks) package; available through the PyPI repository. It covers:

1. Installation
2. Setup and Run on Directory with Structure Files
3. (advanced) Calculating the Formation Energy of all 243 End-Members of 5-Sublattice Sigma Phase (TCP) Ternary System
4. Combining Results from Different Models
5. (advanced) Adding a Custom Model

The release and development branch documentations for pySIPFENN are available at pysipfenn.org or by clicking:

If you are using this software, please cite:

• Adam M. Krajewski, Jonathan W. Siegel, Jinchao Xu, Zi-Kui Liu, Extensible Structure-Informed Prediction of Formation Energy with improved accuracy and usability employing neural networks, Computational Materials Science, Volume 208, 2022, 111254 (https://doi.org/10.1016/j.commatsci.2022.111254)