Active Learning for Materials Design with Kevin Tran

800 800 The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Today we’re joined by Kevin Tran, PhD student in the department of chemical engineering at Carnegie Mellon University.

Kevin’s research focuses on creating and using automated, active learning workflows to perform density functional theory, or DFT, simulations, which are used to screen for new catalysts for a myriad of materials applications. In our conversation, we explore the challenges surrounding one such application—the creation of renewable energy fuel cells, which is discussed in his recent Nature paper “Active learning across intermetallics to guide discovery of electrocatalysts for CO2 reduction and H2 evolution.” We dig into the role and need for good catalysts in this application, the role that quantum mechanics plays in finding them, and how Kevin uses machine learning and optimization to predict electrocatalyst performance.

Giveaway Update!

The O’Reilly Artificial Intelligence Conference is returning to New York in April and we have one FREE conference pass for a lucky listener! To enter:

  • First: Go to to access the entry form.
  • Next: Choose any or all of the nine ways to enter. The more entries you earn, the higher your chances to win!
  • For 3 bonus entries, answer the question at the bottom of the entry box!

About Kevin

Mentioned in the Interview

“More On That Later” by Lee Rosevere licensed under CC By 4.0

Leave a Reply

Your email address will not be published.