The Materials Simulation Toolkit for Machine Learning (MAST-ML): Automating Development and Evaluation of Machine Learning Models for Materials Property Prediction

Explore the Materials Simulation Toolkit for Machine Learning (MAST-ML) in this comprehensive 51-minute tutorial presented by Ryan Jacobs from the University of Wisconsin-Madison. Learn how to automate the development and evaluation of machine learning models for materials property prediction. Dive into hands-on activities covering data import from online databases, data cleaning, feature engineering analysis, model construction and evaluation, and preliminary error analysis and uncertainty quantification. Access the MAST-ML tool on nanoHUB, examine the GitHub repository, and follow along with the step-by-step tutorials. Gain practical insights into importing and cleaning materials datasets, conducting feature engineering, comparing different model types and data splitting techniques, and assessing model performance. Perfect for materials scientists and researchers looking to leverage machine learning in their work.

The Materials Simulation Toolkit for Machine Learning
Tutorial 1: Getting Started with MAST-ML
Tutorial 2: Data Import and Cleaning
Tutorial 3: Feature Engineering
Tutorial 4: Models and Data Splitting Tests
Tutorial 5: Left out data, nested cross validation, and optimized models
Tutorial 6: Model error analysis and uncertainty quantification
Questions