At GE Renewable Energy, CTO Danielle Merfeld and technical leader Arvind Rangarajan are among those making advances throughout renewable energy.
Merfeld and Rangarajan spoke with NVIDIA AI Podcast host Noah Kravitz about how the company uses AI and a human-in-the-loop process to make renewable energy more widespread.
The International Energy Agency has set a goal to reach a net zero energy sector by 2050. To reach this goal, 88 percent of electricity needs to come from renewable sources.
Wind energy will account for 40 percent of that, but today only makes up 8 percent of renewable energy.
Key Points From This Episode:
- Through pretrained models used on image datasets, the team is able to analyze wind turbines for manufacturing defects.
- Given the number of natural disasters on wind turbine farms, field inspectors periodically check the turbines to ensure they’re safe to operate. With AI and digital cameras, the system can preselect 20 photos from a set of 3,000 to help spot potential defects more effectively.
“This AI, supplemented by human-in-the-loop, is really doing a great job of providing value.” — Arvind Rangarajan [19:44]
“There’s a whole new realm here of behaviors, operations, markets and physics — almost boundless opportunities.” — Danielle Merfeld [22:29]
You Might Also Like:
William Tang, principal research physicist at the Princeton Plasma Physics Laboratory, is one of the world’s foremost experts on how the science of fusion energy and HPC intersect. He talks about how he sees AI enabling the quest to deliver fusion energy.
Purple shirts, haircuts and cats. According to deep learning pioneer Andrew Ng, these seemingly disparate things all played a part in AI’s growing presence in our lives. Ng, formerly of Google and Baidu, shares his thoughts on AI being the new electricity.
One of the things that makes the weather so dangerous is that it’s so hard to predict. Knowing when storms may strike can save lives and property. David John Gagne, a postdoctoral fellow at the National Center for Atmospheric Research, is part of a team that’s doing just that. Hear about his work with deep learning.
Subscribe to the AI Podcast
Get the AI Podcast through iTunes, Google Podcasts, Google Play, Castbox, DoggCatcher, Overcast, PlayerFM, Pocket Casts, Podbay, PodBean, PodCruncher, PodKicker, Soundcloud, Spotify, Stitcher and TuneIn. If your favorite isn’t listed here, drop us a note.
Make the AI Podcast Better
Have a few minutes to spare? Fill out this listener survey. Your answers will help us make a better podcast.