Atmosphere Ocean Science Colloquium

---

Neural Operator for Scientific Computing

Speaker: Zongyi Li, California Institute of Technology

Location: Warren Weaver Hall 1302

Date: Wednesday, April 2, 2025, 3:30 p.m.

Synopsis:

Scientific computing, which aims to accurately simulate complex physical phenomena, often requires substantial computational resources. By viewing data as continuous functions, we leverage the smoothness structures of function spaces to enable efficient large-scale simulations. We introduce the neural operator, a machine learning framework designed to approximate solution operators in infinite-dimensional spaces, achieving scalable physical simulations across diverse resolutions and geometries. Beginning with the Fourier Neural Operator, we explore recent advancements including scale-consistent learning techniques and adaptive mesh methods. We demonstrate the real-world impact of our framework through applications in weather prediction and carbon capture, achieving speedups of several orders of magnitude.