» » »

Building Sustainable Artificial Intelligence-Guided Energy Systems from Fundamental Science

Boryann Liaw

Future society needs a sustainable energy supply to support economic growth, and artificial intelligence (AI)-aided, data-driven approaches are rapidly transforming the energy landscape. Sustaining this momentum requires solutions that are both cost effective and energy efficient. The current approach relies on heuristic methods and intensive data acquisition, but resource constraints make rapid deployment difficult. Quantifying returns on investment while accounting for uncertainty and risk adds another major challenge. A trustworthy framework is therefore essential to guide this transformation??"but how can such a framework be built?

Physics-informed framework has been often proposed as a safeguard for the data-driven paradigm. To make this paradigm trustworthy, however, its physics-informed foundation must be reinforced through fundamental science. This presentation will discuss how empirical reduction and induction can strengthen that foundation through quantification and verification. The goal is to ensure that regression-model predictions not only obey fundamental principles but are also quantitatively interpretable. This would connect controlled laboratory test data with real-world, live data streams for practical applications. Because limited data transferability has become a major bottleneck, a quantitative and verifiable physics-informed framework could help overcome it and accelerate a sustainable transformation that is both cost-effective and energy-efficient.

Monday, 11/30/26

Contact:

Website: Click to Visit

Cost:

Free

Save this Event:

iCalendar
Google Calendar
Yahoo! Calendar
Windows Live Calendar

Green Earth Sciences Building

367 Panama St, Room 104
Stanford University
Stanford, CA 94305

Website: Click to Visit