Towards Efficient and Stable Ocean State Forecasting: A Continuous-Time Koopman Approach

arXiv:2603.055606.91 citationsh-index: 3
Predicted impact top 76% in LG · last 90 daysOriginality Incremental advance
AI Analysis

This addresses efficient and stable forecasting for climate modeling, though it is incremental as it builds on existing Koopman and autoencoder methods.

The paper tackled long-horizon ocean state forecasting by developing a Continuous-Time Koopman Autoencoder (CT-KAE) as a lightweight surrogate model, achieving bounded error growth and stable large-scale statistics over 2083-day rollouts, with orders-of-magnitude faster inference compared to numerical solvers.

We investigate the Continuous-Time Koopman Autoencoder (CT-KAE) as a lightweight surrogate model for long-horizon ocean state forecasting in a two-layer quasi-geostrophic (QG) system. By projecting nonlinear dynamics into a latent space governed by a linear ordinary differential equation, the model enforces structured and interpretable temporal evolution while enabling temporally resolution-invariant forecasting via a matrix exponential formulation. Across 2083-day rollouts, CT-KAE exhibits bounded error growth and stable large-scale statistics, in contrast to autoregressive Transformer baselines which exhibit gradual error amplification and energy drift over long rollouts. While fine-scale turbulent structures are partially dissipated, bulk energy spectra, enstrophy evolution, and autocorrelation structure remain consistent over long horizons. The model achieves orders-of-magnitude faster inference compared to the numerical solver, suggesting that continuous-time Koopman surrogates offer a promising backbone for efficient and stable physical-machine learning climate models.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes