Skip to content
Open access

Nonlinear Latent-Space Data Assimilation for Sea Surface Height Reconstruction from Sparse Observations

Sep 2026 · Remote Sensing · 0 citations · 41 references

TL;DR

Latent-LWETKF, a structured latent-space implementation of the localized weighted ensemble transform Kalman filter, is developed, supporting tractable nonlinear ensemble analysis with 40 members while retaining physical observation geometry and complete-field decoding context.

Abstract

Estimating multiscale ocean-surface states from sparse observations is challenging because the state is high-dimensional, sampling is irregular, and posterior distributions can be strongly non-Gaussian. We develop Latent-LWETKF, a structured latent-space implementation of the localized weighted ensemble transform Kalman filter. A convolutional autoencoder maps sea surface height (SSH) fields to spatially organized latent tensors, and nonlinear ensemble analysis updates one active block at a time. The active analysis dimension is the number of scalar latent coordinates updated jointly in that block. Each block proposal is reinserted into the complete member-specific latent state and decoded before its likelihood is evaluated through the original physical-space observation operator, reducing the active dimension while retaining large-scale and cross-block context. The method is evaluated in a coupled fast-slow Lorenz-63 system and a GLORYS12V1-based closed-loop SSH reconstruction experiment over the Luzon Strait. Relative to a local particle filter, it more accurately recovers empirical marginals, low-probability states, and innovation-increment relationships. Relative to the learning-based SSH reconstruction benchmark 4DVarNet-SSH, it reduces RMSE by 10.2%, 12.6%, 8.1%, 7.5%, and 3.4% at observation ratios of 1%, 3%, 5%, 10%, and 20%, respectively. In the Luzon Strait experiments, gains increase with distance from observations and decreasing local coverage, supporting tractable nonlinear ensemble analysis with 40 members while retaining physical observation geometry and complete-field decoding context.

Read PDF

Similar papers

Open access Aug 2026

A Coordinate-Based Framework for Sea Surface Wind Speed Reconstruction from Sparse Multi-Source Observations

Under ERA5-based evaluation, SwiftWind consistently outperforms existing data-driven baselines, including Fourier Neural Operator and Vision Transformer models, demonstrating robustness to observation number, noise level, and spatial distribution.

Ruisheng Hu, Jia-Qi Ding, Jin-Hui Yang et al. · 0 citations
Oct 2026

A Variationally Constrained Attention Model for Sea Surface Height Reconstruction With Multisource Observations

Sea surface height (SSH) is a key variable for characterizing ocean dynamics, yet its high-resolution reconstruction remains challenging due to sparse satellite observations and the limited ability of conventional methods to represent multiscale nonlinear processes. This study proposes a physics-constrained SSH reconst...

Xue-Rong Cui, Yuan-Hao Fang, Juan Li et al. · 0 citations
#diffusion models Open access Sep 2026

DIRECT 1.0: a diffusion-based generative model for dense sea surface temperature reconstructions from sparse satellite observations

DI, a conditional generative framework for dense SST reconstruction that models the full distribution of plausible solutions rather than a single deterministic estimate, is introduced, enabling reliable SST reconstruction from sparse satellite observations.

Grega Rovšček, M. Ličer, A. Barth et al. · 0 citations
Sep 2026

Full-Field Reconstruction from Sparse Observations Using Multiscale Gaussian Kernel and Factorized Fourier Neural Operators

Reconstructing high-dimensional physical fields from sparse observations is a central challenge in subsurface monitoring, where dense measurements are often impractical or unavailable. Existing approaches typically require dense full-state supervision, limiting their applicability when only sparse measurements are av...

R. Wibawa, B. Jha · 0 citations
Sep 2026

Distribution-respecting Model-space Vertical Localization for the Non-Variational Ensemble Data Assimilation of nonlocal Observations: Formulation and Experiments with Clear-sky Infrared Radiances

Operational meteorological ensemble data assimilation (EnsDA) systems frequently assimilate satellite radiance observations. These observations are non-local because they represent spatially-integrated atmospheric information. For ensemble Kalman filters (EnKFs), model-space localization has been hypothesized to be s...

Man-Yau Chan, E. Satterfield, J. Rubin · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.