pySIPFENN

py (S tructure - I nformed P rediction of F ormation E nergy using N eural N etworks) software package allows efficient predictions of the energetics of atomic configurations. The underlying methodology and implementation is given in

• 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)

While functionalities are similar to the software released along the paper, this package contains improved methods for featurizing atomic configurations. Notably, all of them are now written completely in Python, removing reliance on Java and making extensions of the software much easier thanks to improved readability.

News

• (v0.15.0) A new descriptor (feature vector) calculator descriptorDefinitions.KS2022_randomSolutions has been implemented. It is used for structure informed featurization of compositions randomly occupying a lattice, spiritually similar to SQS generation, but also taking into account (1) chemical differences between elements and (2) structural effects. A full description will be given in the upcoming manuscript.

• (v0.14.0) Users can now take advantage of a Prototype Library to obtain common structures from any Calculator instance c with a simple c.prototypeLibrary['BCC']['structure']. It can be easily updated or appended with high-level API or by manually modifyig its YAML here.

• (v0.13.0) Model exports (and more!) to PyTorch, CoreML, and ONNX are now effortless thanks to core.modelExporters module. Please note you need to install pySIPFENN with dev option (e.g., pip install "pysipfenn[dev]") to use it. See docs here.

• (v0.12.2) Swith to LGPLv3 allowing for integration with proprietary software developed by CALPHAD community, while supporting the development of new pySIPFENN features for all. Many thanks to our colleagues from GTT-Technologies and other participants of CALPHAD 2023 <https://calphad.org/calphad-2023>`__ for fruitful discussions.

• (March 2023 Workshop) We would like to thank all of our amazing attendees for making our workshop, co-organized with the Materials Genome Foundation, such a success! Over 100 of you simultaneously followed all exercises and, at the peak, we loaded over 1,200GB of models into the HPC’s RAM.

Note

This project is under active development. We recommend using released (stable) versions.

Index

Contents

• Install pySIPFENN
  • Standard
  • Developer Install
• pySIPFENN API
  • Subpackages
• Exporting pySIPFENN Models
  • General Information
  • ONNXExporter
  • PyTorch
  • CoreML
• FAQ
  • First things to check
  • Known problems with easy solutions
  • More Complex Issues
• Miscellaneous Notes for Users
  • General Useful Tips
  • pySIPFENN Tricks
  • Experimental
• pySIPFENN MGF-PSU Workshop (Feb 2023)
  • Install pySIPFENN
  • Starting pySIPFENN
  • Simple run from directory
  • Sigma-Phase 5-sublattice model
  • Run models utilizing different descriptor / feature vector
  • Add a new model!
• Journal Article
• Changelog
  • v0.15.0
  • v0.13.1
  • v0.13.0
  • v0.12.2
  • v0.12.1
  • v0.12.0
  • v0.11.0post1
  • v0.11.0
  • v0.10.3
  • v0.10.2
  • v0.10.1
• Contributing
  • What to Contribute
  • Rules for Contributing
• Index

Applications

pySIPFENN is a very flexible tool that can, in principle, be used for the prediction of any property of interest that depends on an atomic configuration with very few modifications. The models shipped by default are trained to predict formation energy because that is what our research group is interested in; however, if one wanted to predict Poisson’s ratio and trained a model based on the same features, adding it would take minutes. Simply add the model in open ONNX format and link it using the models.json file, as described in the documentation.

Real-World Examples

In our line of work, pySIPFENN and the formation energies it predicts are usually used as a computational engine that generates proto-data for creation of thermodynamic databases (TDBs) using ESPEI (https://espei.org). The TDBs are then used through pycalphad (https://pycalphad.org) to predict phase diagrams and other thermodynamic properties.

Another of its uses in our research is guiding the Density of Functional Theory (DFT) calculations as a low-cost screening tool. Their efficient conjunction then drives experiments leading to the discovery of new materials, as presented in these two papers:

• Sanghyeok Im, Shun-Li Shang, Nathan D. Smith, Adam M. Krajewski, Timothy Lichtenstein, Hui Sun, Brandon J. Bocklund, Zi-Kui Liu, Hojong Kim, Thermodynamic properties of the Nd-Bi system via emf measurements, DFT calculations, machine learning, and CALPHAD modeling, Acta Materialia, Volume 223, 2022, 117448, https://doi.org/10.1016/j.actamat.2021.117448.

• Shun-Li Shang, Hui Sun, Bo Pan, Yi Wang, Adam M. Krajewski, Mihaela Banu, Jingjing Li & Zi-Kui Liu, Forming mechanism of equilibrium and non-equilibrium metallurgical phases in dissimilar aluminum/steel (Al–Fe) joints. Nature Scientific Reports 11, 24251 (2021). https://doi.org/10.1038/s41598-021-03578-0