OceanVerse: Evaluable 4D Ocean Element Reconstruction Dataset under Realistic Sparsity

OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations

OceanDepths is introduced, the first open, global, regridded AI-ready dataset that pairs satellite-derived sea surface temperature, sea surface salinity, and sea surface height products with co-located EN4 subsurface temperature and salinity profiles, complemented by matched GLORYS12 ocean reanalysis data to support comparisons or multi-stage learning.

Hybrid Graph Learning Reconstructs Global Ocean Oxygen Spatiotemporal Changes

Climate change and anthropogenic activities have exacerbated hypoxic conditions in the global ocean, posing a serious threat to marine ecosystems. Quantifying changes in dissolved oxygen levels is crucial for understanding the impact of these factors on marine life and earth sustainability. However, dissolved oxygen observations are severely sparse, limiting comprehensive analysis. Here we present Jingwei, a 4D spatiotemporal graph transfer learning model that reconstructs ocean oxygen levels globally over the past six decades on a 1◦ x 1◦ grid, covering depths of 0-5500 meters. Jingwei simultaneously leverages intra-profile knowledge transfer using a pattern bank from simulations and captures inter-profile correlations through zoning-varying message passing among observations. It significantly reduces reconstruction error by 27.26% compared to CMIP6, demonstrates high consistency with cruise surveys, and provides satisfactory visual quality. Furthermore, Jingwei produces interpretable results, effectively identifying vertical profile patterns and distinguishing fine-grained spatial distributions. Jingwei provides cartography and quantitative analysis of oxygen minimum zones (OMZ) evolution since 1960. We foresee Jingwei revolutionizing observation-based ocean modeling and deepening our understanding of the breathless ocean. Alongside, we have released an open-source online platform (https://jingwei.acemap.info/ https://jingwei.acemap.info/), providing data visualization, resource sharing and ongoing updates.

OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems

OceanBench is a benchmark designed to evaluate and accelerate global short-range data-driven ocean forecasting, constructed from a curated dataset comprising first-guess trajectories, nowcasts, and atmospheric forcings from operational physical ocean models, typically unavailable in public datasets due to assimilation cycles.

4DVarGen: A 4D Variational-Inspired Generative Model for Eddy-Resolving Surface Ocean Reconstruction

OceanLight: Efficient Global Ocean Forecasting via Geometry-Adaptive Unstructured Mesh Representation

Reliable global ocean forecasting is critical for climate monitoring, marine navigation, and extreme event early warning. Physics-based ocean forecasting models impose prohibitive computational costs, while existing deep learning approaches predominantly rely on structured-grid architectures, incurring unnecessary computation on masked land cells and enforcing uniform resolution across dynamically heterogeneous ocean regions regardless of local flow complexity. Here we present OceanLight, an efficient global ocean forecasting framework innovatively combining geometry-adaptive unstructured mesh tokenization with a graph neural network (GNN) backbone. OceanLight achieves pointwise forecast accuracy and kinetic energy spectral fidelity exceeding both operational numerical analyses and state-of-the-art AI-based models, while surpassing all AI-based ocean models in geostrophic balance consistency. Furthermore, OceanLight demonstrates reliable mesoscale eddy representation, capturing coherent ocean structures beyond pointwise statistical optimization. These capabilities are delivered with a 62% reduction in GPU memory consumption and 70\% reduction in FLOPs relative to structured-grid baselines. Our unstructured mesh representation establishes a generalizable paradigm for scalable data-driven oceanography.

An Intelligent Reconstruction Method for Ocean Subsurface Temperature Empowered by isQG

High-precision reconstruction of subsurface ocean temperatures is of great significance for the identification and monitoring of mesoscale phenomena and the prediction of climate change trends. Although advanced artificial intelligent (AI) algorithms have been widely applied to reconstruct subsurface thermohaline fields from surface inputs, most of them cannot be trained on in situ data because of the sparsity and discontinuity of Argo profiles. Considering Argo profiles as labels, only one-dimensional AI algorithms are applicable thus far, and they cannot fully capture the spatiotemporal evolutionary characteristics of the ocean. As a basic property of mesoscale to larger-scale oceans, quasi-geostrophic (QG) dynamics can help estimate the interior parameters of the ocean. Combining QG with AI algorithms is promising for improving the performance of subsurface reconstruction, which has not been fully exploited by current studies. In this study, a hybrid dynamic-statistical reconstruction framework named interior+surface quasi-geostrophic (isQG)-empowered ResNet is proposed, which is based on the one-dimensional residual network (1D-ResNet) and incorporates the density anomalies reconstructed by the isQG method. The results demonstrate the following. First, the model performance is better than that of the conventional 1D-ResNet model, with the layer-averaged root mean square error being reduced by approximately 0.18 $^{\circ }$C. Shapley additive explanations analysis verifies the important contribution of isQG factors. Second, the predicted temperature profiles are in good agreement with the Argo in situ profiles, reasonably reflecting the vertical temperature variations in actual marine conditions. Third, the reconstructed 3-D temperature field can reasonably represent mesoscale phenomena (e.g., mesoscale eddies) and is in line with the GLORYS12V1 reanalysis data. It is suggested that the proposed method is a feasible and stable framework for subsurface reconstruction and is, thus, helpful for analyzing the three-dimensional structures of mesoscale phenomena.