# 151. Battery Chemistry GPT

- Show: [The Next Byte Podcast](https://hardwarepodcasts.com/podcast/the-next-byte-podcast)
- Published: 2023-12-05
- Length: 23m
- Page: https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2023-12-05-151-battery-chemistry-gpt
- Listen: https://the-next-byte-wevolver.simplecast.com/episodes/151-battery-chemistry-gpt-3eONwQlA

## Summary

Hosts Daniel and For Bode discuss a University of Michigan project developing a GPT-style AI to design battery electrolytes, aiming to lower EV costs and improve energy density. The team utilizes the Polaris supercomputer and partners with Deep Forest Sciences, adapting drug discovery methods to material science to predict viable electrode-electrolyte pairings. They highlight how this AI-driven approach, combined with automated robotics for testing, could accelerate the discovery of sustainable, affordable battery chemistries for the construction and consumer EV markets.

## Chapters

- [0:00](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2023-12-05-151-battery-chemistry-gpt#t=0) Introduction: University of Michigan Battery Chemistry AI
- [0:44](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2023-12-05-151-battery-chemistry-gpt#t=44) Sponsor Read: SAE International and Construction EVs
- [4:27](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2023-12-05-151-battery-chemistry-gpt#t=267) The Problem: Electrolyte Bottlenecks and EV Cost
- [8:01](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2023-12-05-151-battery-chemistry-gpt#t=481) The Solution: GPT-Style AI and Polaris Supercomputer
- [13:56](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2023-12-05-151-battery-chemistry-gpt#t=836) Partnerships: DOE Funding and Deep Forest Sciences
- [16:36](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2023-12-05-151-battery-chemistry-gpt#t=996) Automation: Robotics and Autonomous Discovery
- [21:40](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2023-12-05-151-battery-chemistry-gpt#t=1300) Conclusion and Community Wrap-up

## Topics

- [Batteries & low-power design](https://hardwarepodcasts.com/topic/batteries-and-low-power)
- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Energy & climate tech](https://hardwarepodcasts.com/topic/energy-and-climate-tech)
- [Robotics & autonomy](https://hardwarepodcasts.com/topic/robotics-and-autonomy)

## Most relevant to

early-stage companies

## Mentioned

- University of Michigan (company)
- SAE International (company)
- Polaris (other)
- Deep Forest Sciences (company)
- Department of Energy (company)
- Wevolver (company)

## Related episodes from other shows

- [3D electrodes for Next Generation Batteries with Moshiel Biton, CEO and Co-founder of Addionics](https://hardwarepodcasts.com/podcast/hardware-to-save-a-planet/2022-10-13-3d-electrodes-for-next-generation-batteries-with-moshiel-biton-ceo-and-co-founde) (Hardware to Save a Planet)
- [AI for climate: a real world test](https://hardwarepodcasts.com/podcast/catalyst/2023-06-15-ai-for-climate-a-real-world-test) (Catalyst)
- [The non-Stinky Car](https://hardwarepodcasts.com/podcast/the-amp-hour/2024-03-20-the-non-stinky-car) (The Amp Hour)
- [Can AI revolutionize materials discovery?](https://hardwarepodcasts.com/podcast/catalyst/2024-09-19-can-ai-revolutionize-materials-discovery) (Catalyst)
- [Episode 114: Reducing waste with robotics - Josie Gotz](https://hardwarepodcasts.com/podcast/robot-talk/2025-03-21-episode-114-reducing-waste-with-robotics-josie-gotz) (Robot Talk)

## Citing this page

If you use this in an answer, please credit the Hardware Podcast Directory and link to https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2023-12-05-151-battery-chemistry-gpt. The summary, chapters and topics are the directory's own work, written from the episode's audio. The episode itself, its title and its audio belong to The Next Byte Podcast.