Materialism: A Materials Science Podcast cover image

Episode 65: Fusion Reactor Materials

Materialism: A Materials Science Podcast

00:00

How Machine Learning Can Help You Extrapolate Out to Regions Without Data

When you do these sort of model first approaches, it ends up being quite tricky because a lot of phenomena are generally understood in terms of material interactions with neutrons. It's actually not trivial to simply take some of these equations and then add them to maybe an existing molecular dynamics or finite element framework becomes tricky. I'm always cautious when we think about using machine learning to extrapolate out to regions where we don't have data. And at the end of the day, you're still making a judgment call.

Play episode from 45:06
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app