model_cards/article.md

Model documentation & parameters

Parameters

Property

The supported properties are:

• Metal NonMetal Classifier: Classifying whether a crystal could be metal or nonmetal using a RandomForest classifier
• Metal Semiconductor Classifier: Classifying whether a crystal could be metal or semiconductor using the CGCNN framework.
• Poisson Ratio: Predicted using the CGCNN framework.
• Shear Moduli: Predicted using the CGCNN framework.
• Bulk Moduli: Predicted using the CGCNN framework.
• Fermi Energy: Predicted using the CGCNN framework.
• Band Gap: Predicted using the CGCNN framework.
• Absolute Energy: Predicted using the CGCNN framework.
• Formation Energy: Predicted using the CGCNN framework.

Input file for crystal model

The file with information about the metal. Dependent on the property you want to predict, the format of the file differs:

• Metal NonMetal Classifier. It requires a single .csv file with the metal (chemical formula) in the first column and the crystal system in the second.
• All others: Predicted with CGCNN. The input can either be a single .cif file (to predict a single metal) or a .zip folder which contains multiple .cif (for batch prediction)

Model card - CGCNN

Model Details: Eight CGCNN models trained to predict various properties for crystals.

Developers: CGCNN's developers.

Distributors: Original authors' code wrapped and distributed by GT4SD Team (2023) from IBM Research.

Model date: 2018.

Algorithm version: Models trained and distributed by the original authors.

• Metal Semiconductor Classifier: Model trained to classify whether a crystal could be metal or semiconductor using instances from this database that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals..
• Poisson Ratio: Model to predict the Poisson ratio trained on 2041 instances from this database that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals.
• Shear Moduli: Model to predict the Shear moduli trained on 2041 instances from this database that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit log(GPa).
• Bulk Moduli: Model to predict the Bulk moduli trained on 2041 instances from this database that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit log(GPa).
• Fermi Energy: Model to predict the Fermi energy trained on 28046 instances from this database that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit eV.
• Band Gap: Model to predict the Band Gap trained on 16458 instances from this database that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit eV.
• Absolute Energy: Model to predict the Absolute energy trained on 28046 instances from this database that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit eV/atom.
• Formation Energy: Model to predict the formation energy trained on 28046 instances from this database that includes a diverse set of inorganic crystals ranging from simple metals to complex minerals. Unit eV/atom.

Model type: Crystal Graph Convolutional Neural Networks (CGCNN) that take an arbitary crystal structure to predict material properties.

Information about training algorithms, parameters, fairness constraints or other applied approaches, and features: See the CGCNN paper for details.

Paper or other resource for more information: The CGCNN paper. See the source code for details.

License: MIT

Where to send questions or comments about the model: Open an issue on CGCNN repo.

Intended Use. Use cases that were envisioned during development: Materials research.

Primary intended uses/users: Researchers using the model for model comparison or research exploration purposes.

Out-of-scope use cases: Production-level inference, producing molecules with harmful properties.

Factors: N.A.

Metrics: N.A.

Datasets: Different ones, as described under Algorithm version.

Ethical Considerations: No specific considerations as no private/personal data is involved. Please consult with the authors in case of questions.

Caveats and Recommendations: Please consult with original authors in case of questions.

Model card prototype inspired by Mitchell et al. (2019)

Model card - RandomForestMetalClassifier

Model Details: A RandomForest model to classify whether a crystal could be a metal or nonmetal.

Developers: SemiconAI repo's developers.

Distributors: Original authors' code wrapped and distributed by GT4SD Team (2023) from IBM Research.

Model date: 2022.

Algorithm version: Models trained and distributed by the original authors.

• Metal NonMetal Classifier: Model trained to classify whether a crystal could be metal or nonmetal.

Model type: A metal/nonmetal classifier for crystals based on the RandomForest algorithm.

Information about training algorithms, parameters, fairness constraints or other applied approaches, and features: See the original paperl for details.

Paper or other resource for more information: The original paper. See the source code for details.

License: MIT

Where to send questions or comments about the model: Open an issue on SemiconAI repo.

Intended Use. Use cases that were envisioned during development: Materials research.

Primary intended uses/users: Researchers using the model for model comparison or research exploration purposes.

Out-of-scope use cases: Production-level inference, producing molecules with harmful properties.

Factors: N.A.

Metrics: N.A.

Datasets: See Algorithm version.

Ethical Considerations: No specific considerations as no private/personal data is involved. Please consult with the authors in case of questions.

Caveats and Recommendations: Please consult with original authors in case of questions.

Model card prototype inspired by Mitchell et al. (2019)

Citation

@article{PhysRevLett.120.145301,
  title = {Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties},
  author = {Xie, Tian and Grossman, Jeffrey C.},
  journal = {Phys. Rev. Lett.},
  volume = {120},
  issue = {14},
  pages = {145301},
  numpages = {6},
  year = {2018},
  month = {Apr},
  publisher = {American Physical Society},
  doi = {10.1103/PhysRevLett.120.145301},
  url = {https://link.aps.org/doi/10.1103/PhysRevLett.120.145301}
}

@article{siriwardane2022generative,
  title={Generative design of stable semiconductor materials using deep learning and density functional theory},
  author={Siriwardane, Edirisuriya M Dilanga and Zhao, Yong and Perera, Indika and Hu, Jianjun},
  journal={npj Computational Materials},
  volume={8},
  number={1},
  pages={164},
  year={2022},
  publisher={Nature Publishing Group UK London}
}