Skip to content
Open access

Reconstructing subsurface temperature fields from single-point time series: a metric learning approach in the South China Sea

Sep 2026 · Frontiers in Marine Science · Vol 13 · 0 citations · 25 references

Abstract

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 underutilized in existing frameworks—where point measurements are typically reduced to daily means or treated as static interpolation nodes. This study investigates a fundamental question: can single-point time series encode sufficient spatial information to reconstruct the surrounding temperature field? To address this, we propose a metric learning-based framework that learns to align temporal features with spatial patterns in a shared latent space, enabling spatial inversion from single-point time series. The framework is validated using the 100 m depth temperature field in the northern South China Sea, derived from a high-resolution reanalysis product. Results show that temporal and spatial features exhibit no significant correlation when optimized solely for reconstruction; after metric learning-based joint adjustment, they form clear cluster structures in the latent space. The reconstructed spatial fields capture the dominant modes of oceanic features, primarily internal wave-related spatial patterns, though fine-scale details remain limited. Quantitative evaluation yields an RMSE of 0.12 °C and an R² of 0.21, providing the first quantified evidence for the feasibility of the “time-depth for spatial-breadth” strategy. These findings suggest that single-point temporal dynamics encode meaningful spatial information, offering a new perspective for sparse-observation ocean state estimation.

Read PDF

Similar papers

Preprint Nov 2026

PARDIG: Global Precipitation Estimates Learned from Sparse Satellite Observations

Estimating precipitation at the global scale is vital for Earth system science and disaster response, yet observational coverage and measurement precision remain constrained. Existing solutions provide options that trade off desirable traits such as skill, latency, geographical coverage, temporal coverage, and spatial...

Guy Shalev, S. Rasp, B. Babenko et al. · 0 citations
Open access Nov 2026

Machine-learning reconstruction of ERA5-Land temperature at local administrative units

Extreme climate impacts are often managed at neighborhood and local administrative scales, yet reanalysis products remain spatially coarse and are not aligned with administrative boundaries such as Census Block Groups (CBGs). This study develops a machine-learning-based change-of-support reconstruction workflow to tr...

C. Ibebuchi, M. Richman, S. Sherchan et al. · 0 citations
Preprint Oct 2026

TerraNostra-Bench: Benchmarking Spatial Downscaling and Temporal Rollout for Global 1-km Land-Use Reconstruction

Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly due to imperfect land surface representations in Earth system models. We propose a data-driven framework for high-resolution land-use reconstruction, treated as a semantic-segmentation task, that combines coarse-resolu...

A. Mozaffari, M. Castaño, S. Materia et al. · 0 citations
#diffusion models Open access Oct 2026

NeuPlume: generative inversion of atmospheric point-source emissions from sparse observations

NeuPlume is presented, a neural-physical framework that formulates inversion as observation-guided generation and selection of complete three-dimensional concentration fields and provides an extensible methodology for jointly estimating source parameters and concentration fields.

Lei Wang, Xin Ma · 0 citations
Nov 2026

Multiple-driven near-offset seismic data reconstruction based on deep learning

Near-offset data gaps are a systematic feature of marine streamer acquisition whose accurate reconstruction is critical for multiple attenuation, velocity analysis, and shallow subsurface imaging. Existing methods — whether based on prediction-error filters, transform-domain sparsity, or supervised deep learning — rely...

Zhi-Na Li, Zhi-Chuan Yu, Zhen-Chun Li et al. · 0 citations

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