Generalizable Implicit Neural Representations via Parameterized Latent Dynamics for Baroclinic Ocean Forecasting (Papers Track)
Guang Zhao (Brookhaven National Lab); Xihaier Luo (Brookhaven National Lab); Seungjun Lee (Brookhaven National Lab); Yihui Ren (Brookhaven National Lab); Shinjae Yoo (Brookhaven National Lab); Luke Van Roekel (Los Alamos National Laboratory); Balu Nadiga (Los Alamos National Laboratory); Sri Hari Krishna Narayanan (Argonne National Laboratory); Yixuan Sun (Argonne National Laboratory); Wei Xu (Brookhaven National Lab)
Abstract
Mesoscale ocean dynamics play a critical role in climate systems, governing heat transport, hurricane genesis, and drought patterns. However, simulating these processes at high resolution remains computationally prohibitive due to their nonlinear, multiscale nature and vast spatiotemporal domains. Implicit neural representations (INRs) reduce the computational costs as resolution-independent surrogates but fail in many-query scenarios (inverse modeling) requiring rapid evaluations across diverse parameters. We present \textbf{PINROD}, a novel framework combining dynamics-aware implicit neural representations with parametrized neural ordinary differential equations to address these limitations. By integrating parametric dependencies into latent dynamics, our method efficiently captures nonlinear oceanic behavior across varying boundary conditions and physical parameters. Experiments on ocean mesoscale activity data show superior accuracy over existing baselines and improved computational efficiency compared to standard numerical simulations.