不完整观测提升海洋建模中的进化性能
Incomplete Observations Boost Evolutionary Performance in Ocean Modeling
浏览论文内容
中文总结 AI 辅助
研究提出基于隐马尔可夫模型的生成状态空间模型及优化框架，能从稀疏观测学习，通过期望最大化算法训练，交替重建与优化，实验验证其可提升海洋建模性能，为地球系统模型提供新途径。
中文摘要 AI 辅助
数据驱动方法革新了海洋建模，但当前方法严重依赖完整再分析数据集，存在计算限制并将模型性能局限于训练数据。本文提出生成状态空间模型和优化框架，能直接从稀疏且有噪声的观测中学习。该模型本质是具有连续状态空间的隐马尔可夫模型，将海洋物理量视为隐藏状态，测量值视为观测值。通过基于期望最大化算法推导优化框架来训练模型，交替通过朗之万动力学重建高保真海洋场并优化深度神经网络。实验表明稀疏观测可直接改善模型对海洋状态动力学的表示，为下一代地球系统模型提供了可扩展途径。
英文摘要
Data-driven methods have revolutionized ocean modeling, yet current approaches rely heavily on complete reanalysis datasets, imposing computational constraints and limiting model performance to that of the training data. Here, we present a generative state-space model and an optimization framework that enable learning directly from sparse and noisy observations. The model is essentially a hidden Markov model with a continuous state space, where oceanic physical quantities are treated as hidden states and measurements as observations, enabling a unified representation of ocean fields and observational data. Both the initial-state and state-transition modules are implemented as neural networks to capture the complexity and temporal evolution of ocean states, while the emission module is formulated as a masked Gaussian distribution. To train the model from sparse observations, we derive an optimization framework based on the expectation-maximization (EM) algorithm. The framework alternately reconstructs high-fidelity ocean fields via Langevin dynamics and optimizes deep neural networks to capture temporal evolution. Theoretical analysis shows that the framework maximizes the likelihood of observations under the generative model. For efficiency, we assume that ocean-state evolution follows a stationary, ergodic, and Markovian stochastic process and adopt only length-two state sequences during optimization. Experiments on CMIP6 simulation data and FY-3D satellite data demonstrate high-fidelity reconstruction and accurate prediction, showing that sparse observations can directly improve the model's representation of ocean-state dynamics. This work offers a scalable pathway for next-generation Earth system models to learn directly from sparse, incomplete real-world observations.
发表机构
- Ocean University of China（中国海洋大学）
- School of Computer Science and Technology, Ocean University of China（中国海洋大学计算机科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。
