SOURCE-LINKED INTELLIGENCE

OceanMoE: Structured Conditional Sparse Computation for Long-Horizon Multivariate Ocean Forecasting

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Multivariate ocean forecasting must exploit shared evolution in a coupled ocean system while adapting to the heterogeneous statistical and dynamical characteristics of different prediction variables and locations. Fully shared models may lack the flexibility to handle this heterogeneity, whereas fully independent models discard the common ocean context shared across variables. The key question is how to retain shared context in a unified model while allowing computation to specialize according to the prediction target and local state. We propose OceanMoE, a structured conditional sparse Mixtur

Read original source ↗ Open in workspace

recordType

paper

region

Global