OceanMoE：面向长时程多变量海洋预报的结构化条件稀疏计算
OceanMoE: Structured Conditional Sparse Computation for Long-Horizon Multivariate Ocean Forecasting
浏览论文内容
中文总结 AI 辅助
OceanMoE提出结构化条件稀疏混合专家框架，通过内容条件路由与地理偏差平衡共享背景与特化，在长时程ORAS5预报中降低误差并保持优势。
中文摘要 AI 辅助
多变量海洋预报必须利用耦合海洋系统中的共享演化，同时适应不同预测变量和位置在统计与动力学特征上的异质性。完全共享的模型可能缺乏处理这种异质性的灵活性，而完全独立的模型则丢弃了各变量间共享的海洋背景信息。关键问题在于，如何在统一模型中保留共享背景，同时允许计算根据预测目标和局部状态进行特化。我们提出OceanMoE，一种结构化条件稀疏混合专家框架，结合共享与特化以支持多变量海洋预报。OceanMoE融合跨变量信息以构建目标特定的局部表示，并利用这些表示在每个空间位置执行内容条件稀疏路由，其中活跃专家数量根据路由器置信度自适应调整。在解码器中，路由通过由球谐空间基参数化的学习地理偏差进行增强，而共享残差和季节路径提供常见的跨变量及月份依赖背景。在长时程自回归ORAS5预报上的实验表明，OceanMoE在两种评估设置下均降低了总体预报误差，并在大多数后续滚动月份中保持比相应基线更低的几何平均归一化均方根误差。路由分析进一步表明，专家分配随预测目标和空间位置而变化。这些结果支持结构化条件计算作为平衡共享海洋背景与自适应特化的建模策略。
英文摘要
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 Mixture-of-Experts framework that combines sharing and specialization for multivariate ocean forecasting. OceanMoE fuses cross-variable information to construct target-specific local representations and uses them to perform content-conditioned sparse routing at each spatial location, with the number of active experts adapted to router confidence. In the decoder, routing is augmented with a learned geographic bias parameterized by spherical-harmonic spatial bases, while shared residual and seasonal pathways provide common cross-variable and month-dependent context. Experiments on long-horizon autoregressive ORAS5 forecasting show that OceanMoE lowers aggregate forecasting error in both evaluated settings and maintains lower geometric-mean normalized RMSE than the corresponding baselines over most later rollout months. Routing analyses further show that expert allocation varies with prediction targets and spatial locations. These results support structured conditional computation as a modeling strategy for balancing shared ocean context with adaptive specialization.
发表机构
- Hangzhou Institute for Advanced Study, University of the Chinese Academy of Sciences（中国科学院大学杭州高等研究院）
- Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）
机构由 AI 辅助整理，请以论文原文为准。
