Machine Learning for Defect Analysis in Materials Simulations

  • Construction of Feature Vectors from Materials Structure Data
  • Support Vector Machine for defect classification
  • Greater than 99% accuracy in classification of point and extended defects
True and ML-Predicted labels for defects in a Nano-indented sample of Nickel

The python-based machine learning module identifies and classifies different point and extended defects in crystal structure data generated by atomistic simulations, by learning information about local atomic structure.