Wed., Jul. 22 | Online Webinar

Applications of Machine Learning in Battery Research

Have you ever wondered how machine learning could be used in a research field such as battery research? Dr. Kristen Severson, post doctoral fellow at IBM, joins us in an online webinar to share her work in this field and answer our burning questions!
Registration is Closed
Applications of Machine Learning in Battery Research

Time & Location

Jul. 22, 2020, 10:30 a.m. – 11:45 a.m. EDT
Online Webinar

About the event

About the speaker

Dr. Kristen Severson is a post-doctoral researcher at IBM Research in Cambridge, MA. Her interests are broadly in applied machine learning with a current focus on healthcare applications. Prior to joining IBM, Kristen earned her PhD at MIT where she worked on machine learning applied to problems in lithium-ion batteries, production oil wells, and bioinformatics. She also holds a BS from Carnegie Mellon University.

Webinar abstract

Accurately predicting the lifetime of complex, nonlinear systems such as lithium-ion batteries is critical for accelerating technology development. However, diverse aging mechanisms, significant device variability and dynamic operating conditions have remained major challenges. We generate a comprehensive dataset consisting of 124 commercial lithium iron phosphate/graphite cells cycled under fast-charging conditions, with widely varying cycle lives ranging from 150 to 2300 cycles. Using discharge voltage curves from early cycles yet to exhibit capacity degradation, we apply machine-learning tools to both predict and classify cells by cycle life. Our best models achieve 9.1% test error for quantitatively predicting cycle life using the first 100 cycles. The resulting model is then used in a Bayesian optimization framework for design of experiments to identify high-cycle-life charging protocols among 224 candidates in only 16 days - as compared with over 500 days using exhaustive search without early prediction. This work highlights the promise of combining deliberate data generation with data-driven modeling and machine learning to predict the behavior of complex dynamical systems and accelerate scientific discovery.

Additional information

  • This event can count towards the seminar attendance milestone of University of Waterloo graduate students in the Department of Chemical Engineering. The link to register your attendance will be provided in the chat box during the webinar and will remain open for a short time only. Please note that you must be present from the beginning to the end of the webinar in order to have your attendance be counted towards your milestone.

This event is open to everyone and we welcome you all to join us!

Share this event