Create An Account Login

2022 MRS Fall Meeting & Exhibit

 

Tutorial DS00—Machine Learning in Materials Science—From Basic Concepts to Active Learning

Sunday, November 27
8:00 am – 5:00 pm
Hynes, Level 2, Room 204

Thursday, December 8
8:00 am – 3:00 pm EST
Virtual Meeting

Thursday, December 8
4:00 pm – 11:00 pm EST
Virtual Meeting

Methods rooted in data science, machine learning, and artificial intelligence have become necessary components of materials design endeavors, being frequently applied in conjunction with both computational and experimental data. The now thriving field of materials informatics has seen the accelerated discovery of new battery materials, solar cell absorbers, thermoelectrics, and routes for autonomous synthesis and characterization. The need to educate and train the materials science workforce on the essential elements of machine learning has never been greater. This tutorial will be part of a recurring series at MRS Spring and Fall Meetings that introduce newcomers to all the basic concepts of machine learning in materials science, walking them through a few interactive examples that use existing datasets and ML resources.


There will be overview presentations of key ML concepts, following which the presenter and audience will together work through Python notebooks that contain easy-to-follow examples from the literature. The audience will likely constitute undergraduate and graduate students looking to get started with materials informatics, but the tutorial will be welcome and useful for any researcher. Some familiarity with writing code and making plots in Python would be useful. The audience is encouraged to run code along with the presenters, on Jupyter notebooks via google collab. There will be a ML hackathon in the afternoon, where attendees will be given a battery dataset and have chances to apply machine learning methods to real-world challenges.   

 

 

Tutorial Schedule

8:00 am
Introduction to Machine Learning for Materials Science 
Arun Mannodi Kanakkithodi, Purdue University

Introduction to ML for materials science, some high-level examples, discussion of nuts and bolts of ML (data pre- and post-processing, descriptors, similarity measures, methods including linear and random forest regression, packages and tools). Demonstration of training ML models using a dataset of perovskite band gaps.

9:30 am 
Break

10:00 am
Gaussian Process Regression—Detailed Description and Walkthrough of Two Examples
Austin McDannald, NIST

10:30 am 
Discussion of Active Learning, Bayesian Optimization and Autonomous Experiments Through an Example
Austin McDannald, NIST

11:30 am
General Discussion 

12:00 pm
Lunch

1:30 pm
Overview of Neural Networks for Prediction and Convolutional Neural Networks for Image Datasets 
Saaketh Desai, Sandia National Laboratories

2:30 pm
General Discussion

3:00 pm
Machine Learning Challenge (open until Thursday, December 1) 
Shijing Sun, Toyota Research Institute

A battery dataset will be assigned to the contestants, who will apply some of the methods discussed during the tutorial and use available scripts to train models and make predictions. Please fill this sign-up form if interested and bring your laptop to the in-person launch at 3:00 pm. 

 

 

 

 

Publishing Alliance

MRS publishes with Springer Nature

Symposium Support