Dataset for the paper 'Predicting mechanical properties of polycrystalline nanopillars by interpretable machine learning'

This dataset contains the data produced for the above paper. The dataset consists of:

- input nanopillars before deformation (molecular_dynamics/nanopillars)

- stress-strain curves acquired by deforming the nanopillars (molecular_dynamics/stress_strain_curves)

- weights of the CNNs trained to predict mechanical properties of the nanopillars (machine_learning/train_CNN)

- Grad-CAM fields of the predictions (machine_learning/train_CNN)

Codes used for creating and analyzing the dataset are available at https://github.com/tekoivisto/nanopillar-ML