Similar papers
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.
· IEEE Sensors Letters · 0 citations
Open access
Sep 2026
Reconstructing subsurface temperature fields from single-point time series: a metric learning approach in the South China Sea
Subsurface ocean observations remain severely limited in spatial coverage due to the high cost and operational difficulty of in-situ deployment. Although moored buoys and profiling floats enable continuous, minute-level sampling at fixed locations, the temporal evolution information they record is largely underutil...
Lu-,-Hong-Feng-,-Li-Zheng-Bao-,-Guo-Zhong-Wen Hong, Meng-Yao Wang, Qing Xu et al.
· Frontiers in Marine Science · 0 citations
Open access
Sep 2026
Nonlinear Latent-Space Data Assimilation for Sea Surface Height Reconstruction from Sparse Observations
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.
Meng-Ge Zhou, Xiao-Qun Cao, Yan Chen et al.
· Remote Sensing · 0 citations
Conference
Open access
Sep 2026
4DVarGen: A 4D Variational-Inspired Generative Model for Eddy-Resolving Surface Ocean Reconstruction
4DVarGen is proposed, a 4DVar-inspired generative framework for reconstructing sea surface variable fields at eddy-resolving scales from sparse remote-sensing observations that establishes a mathematical equivalence between 4DVar and an observation-guided denoising process.
Jun-Peng Huang, Wu-Xin Wang, Xiao-Yong Li et al.
· Proceedings of the Thirty-Fi... · 0 citations
Open access
Mar 2026
Pure and physics-guided deep learning approaches for spatio-temporal groundwater level prediction
An attention-based pure deep learning model is proposed to predict weekly groundwater levels of 28 piezometers in the Cuneo and Torino provinces in Piedmont (Italy), leveraging both irregular groundwater time series and weather image sequences by considering physics-guided strategies to inject the groundwater flow equa...
Matteo Salis, Gabriele Sartor, Rosa Meo et al.
· Machine Learning: Science an... · 0 citations
Deep Learning-Based Meteorological Data Downscaling: A Comparative Study with Physics-Informed CNN and a Component-Level Ablation Analysis
The proposed Physics-Informed CNN (PICNN), which integrates multi-scale feature extraction, spatial attention mechanisms, and a composite physics-informed loss function incorporating mean squared error, Laplacian spatial smoothness regularization, and spatial energy conservation constraints, achieves the best performan...
Johans Utama
· 0 citations