Resources

Rensselaer Polytechnic Institute, 110 8th St, Troy, New York 12180, United States

Materials Intelligence

Rhone Research Group

Self-Learning

Coursera

Machine Learning, Andrew Ng
Data Science, Johns Hopkins University

Textbooks

Introduction to Statistical Learning, Trevor Hastie et al.
Pattern Recognition and Machine Learning, Christopher Bishop
Deep Learning, Ian Goodfellow, Yoshua Bengio and Aaron Courville

Newsletters/Tutorials

A beginner's guide to using data science for physicists
Citrine Newsletter
TensorFlow tutorial
Introduction to Linear Algebra using Python (by Dr. Steven L. Richardson)

Workshops

Data Science Platforms

NIST, REsource for Materials Informatics

Data science tools

Programming tools

Popular programming languages: Python, Julia, R
Jupyter notebook
JupyterHub
Google Colab
Useful python packages: Pandas, Numpy, Matplotlib, Plotly, Sci-kit learn*

Sci-kit learn

Sci-kit learn is a python package that allows you to easily implement many machine learning models. This is a popular data science tool for building models that do not involve neural networks.

Deep learning tools

TensorFlow
Pytorch
Keras

Descriptors

Atomistic simulations

Properties from Artificial Neural Network Architectures (PANNA)
Tensor field networks

Sharing your work

Select publications

Materials Informatics

Krishna Rajan, Materials Today, 38 (2005).

The high-throughput highway to computational materials design

Stefano Curtarolo, Gus L. W. Hart, Marco Buongiorno Nardelli, Natalio Mingo, Stefano Sanvito and Ohad Levy, Nature Materials 12, 191 (2013). DOI: 10.1038/NMAT3568

Data-driven studies of magnetic two-dimensional materials

Rhone, T.D., Chen, W., Desai, S. et al. Data-driven studies of magnetic two-dimensional materials. Sci Rep 10, 15795 (2020). https://doi.org/10.1038/s41598-020-72811-z

Predicting outcomes of catalytic reactions using machine learning

Trevor David Rhone, Robert Hoyt, Christopher R. O'Connor, Matthew M. Montemore, Challa S.S.R. Kumar, Cynthia M. Friend and Efthimios Kaxiras, arXiv:1908.10953

Big Data of Materials Science: Critical Role of the Descriptor

Luca M. Ghiringhelli, Jan Vybiral, Sergey V. Levchenko, Claudia Draxl, and Matthias Scheffler,

PRL 114, 105503 (2015)

A structural approach to relaxation in glassy liquids

S. S. Schoenholz, E. D. Cubuk, D. M., Sussman, E. Kaxiras and A. J. Liu,

Nature Physics 12, 469 (2016), DOI: 10.1038/NPHYS3644

Prediction of Low-Thermal-Conductivity Compounds with First-Principles Anharmonic Lattice-Dynamics C

Atsuto Seko, Atsushi Togo, Hiroyuki Hayashi, Koji Tsuda, Laurent Chaput, and Isao Tanaka,

PRL 115, 205901 (2015).

Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning

M. Rupp, A. Tkatchenko, K.-R. Müller, O.A. von Lilienfeld, Physical Review Letters 108(5): 058301, (2012).

Physical Symmetries Embedded in Neural Networks

M. Mattheakis, P. Protopapas, D. Sondak, M. Di Giovanni, E. Kaxiras, arXiv:1904.08991

Materials Intelligence

Rhone Research Group

resources

Materials-intelligence tutorials

Materials Informatics

Self-Learning

Coursera

Textbooks

Newsletters/Tutorials

Workshops

Data Science Platforms

Data availability

Kaggle datasets

Google's datasets search

Selected materials databases

Data science tools

Programming tools

Sci-kit learn

Deep learning tools

Descriptors

Atomistic simulations

Sharing your work

Select publications

Materials Informatics

The high-throughput highway to computational materials design

Data-driven studies of magnetic two-dimensional materials

Predicting outcomes of catalytic reactions using machine learning

Big Data of Materials Science: Critical Role of the Descriptor

A structural approach to relaxation in glassy liquids

Prediction of Low-Thermal-Conductivity Compounds with First-Principles Anharmonic Lattice-Dynamics C

Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning

Physical Symmetries Embedded in Neural Networks