This tutorial will introduce core concepts of machine learning through the lens of a basic workflow to predict material bandgaps from material compositions. As we progress through this workflow we will highlight key steps, challenges that can come up with materials data, and potential solutions to these challenges. The core workflow we’ll introduce includes: Data Cleaning, Feature Generation, Feature Engineering, Establishing Model Assessment, Training a Default Model, Hyperparameter Optimization, and Making Predictions. By the end of the tutorial I hope that you’ll have a better understanding of these core concepts, and how they can all fit together.

>Benjamin Afflerbach received a B.S in mechanical engineering from Texas A&M University in 2014. He then obtained a Ph. D. in Materials Science and Engineering from the University of Wisconsin – Madison in 2021.

Dr. Afflerbach is currently a Research Associate in the Materials Science and Engineering department at the University of Wisconsin – Madison. His research is focused on using materials informatics to supplement traditional materials science research, with the main focus of this research being on metallic glasses. In addition to research he is heavily involved in management of the undergraduate research group the Informatics Skunkworks through which he has mentored multiple undergraduate research groups, developed educational materials and curriculum for onboarding undergraduate researchers, and built community infrastructure to help grow the group.

Network for Computational Nanotechnology (NCN)

Researchers should cite this work as follows:

• Benjamin Afflerbach (2022), "Introduction to a Basic Machine Learning Workflow for Predicting Materials Properties," https://nanohub.org/resources/36489.

  BibTex | EndNote

1. bandgap
2. computational materials science
3. data-driven materials discovery
4. decision trees
5. hands on
6. machine learning
7. Machine Learning Lab
8. material properties
9. materials science
10. NCN Group - Machine Learning Hands-on