CNN+高斯过程混合框架：稀疏观测下的数据同化与偏差校正
Patch-Based Deep Kernel Learning for Data Assimilation and Bias Correction with Extremely Sparse Observations
气象海洋方向的研究者可以看看：用 CNN 加高斯过程做数据同化，比 3D-Var 快 98% 还带不确定性估计，协方差也能直接替换进 3D-Var。
论文提出一种将 CNN 与可学习核高斯过程（GP）耦合的混合框架，从极稀疏观测中同时完成数据同化（DA）与偏差校正（BC）。模型通过最大化边际对数似然端到端训练，学习整个网格上的数据驱动协方差，并天然输出最大后验估计及不确定性。patch 策略将精确 GP 在 N 个网格点上 O(N³) 的训练成本降到 O(N)，推理只需求解规模取决于观测数 m（m 远小于 N）的线性系统。在海表温度和盐度实验中，该框架在合成与真实稀疏观测上均优于 3D-Var、经典 GP 和一个对比深度学习模型，推理时间比 3D-Var 减少 98% 以上。
Patch-Based Deep Kernel Learning for Data Assimilation and Bias Correction with Extremely Sparse Observations
Data Assimilation (DA) reconstructs the state of a spatio-temporal system by combining sensor observations with the output of a numerical model. Since model states are high-dimensional while observations cover only a small fraction of the domain, DA is a challenging large-scale estimation problem, central to weather forecasting and oceanography. Classical variational methods such as 3D-Var rely on a hand-crafted background error covariance that assumes unbiased errors, and therefore cannot capture state-dependent correlations or systematic model biases. Moreover, their cost grows with the size of the domain. Deep learning (DL) methods can perform DA and bias correction (BC) non-linearly, but typically offer limited interpretability and no calibrated uncertainty estimates. We propose a hybrid framework that couples a convolutional neural network (CNN) with a learnable-kernel Gaussian Process (GP) to jointly perform DA and BC from extremely sparse observations. The model is trained end-to-end by maximizing the marginal log-likelihood, learns a data-driven covariance over the whole grid, and provides both the Maximum A Posteriori analysis and its uncertainty by design. A patch-based strategy reduces the $O(N^3)$ training cost of exact GPs over $N$ grid points to $O(N)$ for a fixed patch size. Inference remains exact and only requires solving a linear system whose $O(m^3)$ cost depends on the number of observations $m \ll N$, not on the domain. The learned covariance can also replace the hand-crafted one in 3D-Var, improving its accuracy without changing the variational formulation. Experiments on sea surface temperature and salinity, with both synthetic and real, extremely sparse in-situ observations, show that the framework outperforms 3D-Var, a classical GP and a competing DL model, while reducing inference time by more than 98% with respect to 3D-Var.