From Atoms to Systems: How AI is Transforming EV Batteries

Artificial Intelligence (AI) has gained increasing global attention for its transformative potential across industries. Alongside robotics, it has become central to efforts aimed at accelerating clean technology and mitigating climate change. At the intersection of AI, automation, and energy storage, several critical questions emerge: What can data-driven approaches achieve that are not possible with traditional methods? Where can they be effectively applied? Do we have sufficient field data? What questions can AI help us address, and where does it fall short? Ultimately, will AI replace scientists in the search for next-generation energy technologies?

In this seminar, we will explore these questions through the lens of electric vehicle (EV) batteries - a rapidly growing field critical to achieving carbon-neutral mobility, which has spurred intensive research, development, and commercial scale-ups over the past few years. I will discuss examples of how data-driven approaches can be applied throughout the life cycle of an EV battery. At the system level, we will discuss how optimizing driving behaviors can conserve battery usage and methods to extend battery lifetime through improved aging predictions. Moreover, we will explore how these models can bridge gaps across different length scales, feeding back into faster, more intelligent R&D processes to shorten the lab-to-market timeline of new battery technologies. Through these examples, we hope to share our efforts in building a collaborative intelligence ecosystem where humans are empowered by AI in the pursuit of a sustainable future.

Speaker: Shijing Sun, University of Washington