Changhong Mou

Turbulent flow surrogates routinely blow up under standard operator inference, but jointly calibrating stochastic drift and diffusion while enforcing energy-preserving symmetries guarantees long-time stability at machine precision.

Neural-POD lets you build resolution-invariant, nonlinear basis functions for complex spatiotemporal systems, outperforming classical POD and bridging the gap between traditional ROM and operator learning.