Machine Learning-Based Nonlinear Nudging for Chaotic Dynamical Systems
By: Jaemin Oh, Jinsil Lee, Youngjoon Hong
Potential Business Impact:
Makes computer models of weather more accurate.
Nudging is an empirical data assimilation technique that incorporates an observation-driven control term into the model dynamics. The trajectory of the nudged system approaches the true system trajectory over time, even when the initial conditions differ. For linear state space models, such control terms can be derived under mild assumptions. However, designing effective nudging terms becomes significantly more challenging in the nonlinear setting. In this work, we propose neural network nudging, a data-driven method for learning nudging terms in nonlinear state space models. We establish a theoretical existence result based on the Kazantzis--Kravaris--Luenberger observer theory. The proposed approach is evaluated on three benchmark problems that exhibit chaotic behavior: the Lorenz 96 model, the Kuramoto--Sivashinsky equation, and the Kolmogorov flow.
Similar Papers
Data assimilation with model errors
Numerical Analysis
Fixes computer weather forecasts when they are wrong.
Universal Learning of Nonlinear Dynamics
Machine Learning (CS)
Learns how things change, even when wobbly.
Lyapunov Learning at the Onset of Chaos
Machine Learning (CS)
Teaches computers to learn new things without forgetting.