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

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

The vast oceans record the impacts of climate change and human activities on the Earth system. Over the past century, oceanographic scientists have collected extensive ocean profile data to reflect variations of oceanic elements, such as dissolved oxygen. However, due to the sophisticated measurements and high costs, historical ocean element observation data remains highly sparse and uneven across the global ocean, with the annual missing rate exceeding 90%. Thus, quantitatively understanding the four-dimensional (4D) spatiotemporal evolution of oceanic elements continues to pose a significant challenge. Machine learning (ML) techniques demonstrate superior capabilities in perceiving spatiotemporal variations within large-scale data, presenting promising opportunities to harness implicit correlations for global reconstruction. However, fragmented data and interdisciplinary differences create barriers to the availability of AI-ready open data, further hindering ML practitioners from designing specialized models. To solve this problem, we present the first oceanic 4D sparse observation reconstruction dataset, named OceanVerse. By integrating nearly 2 million real-world profiles since 1900 and three differentiated Earth system numerical simulation, we construct a comprehensively evaluable dataset with missing patterns that align with real-world conditions through a digital twin sampling. OceanVerse provides a novel large-scale (~100× nodes vs. existing datasets) dataset that meets the MNAR (Missing Not at Random) condition, supporting more effective model comparison, generalization evaluation and potential advancement of scientific reconstruction architectures. The OceanVerse dataset and codebase are publicly available. The OceanVerse resource is available at https://github.com/jingwei-sjtu/OceanVerse.

Wide-swath satellite altimetry and novel subsurface temperature observations improve predictions in a dynamic western boundary current: System optimization and performance

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

Data-driven approaches, particularly those based on deep learning, are rapidly advancing Earth system modeling. However, their application to ocean forecasting remains limited despite the ocean’s pivotal role in climate regulation and marine ecosystems. To address this gap, we present OceanBench, a benchmark designed to evaluate and accelerate global short-range (1-10 days) data-driven ocean forecasting. OceanBench is 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. Matched observational data are also included, enabling realistic evaluation in an operational-like forecasting framework. The benchmark defines three complementary evaluation tracks: (i) Model-to-Reanalysis, where models are compared against the reanalysis dataset commonly used for training; (ii) Model-to-Analysis, assessing generalization to a higher-resolution physical analysis; and (iii) Model-to-Observations, Intercomparison and Validation (IV-TT) CLASS-4 evaluation against independent observational data. The first two tracks are further supported by process-oriented di-agnostics to assess the dynamical consistency and physical plausibility of forecasts. OceanBench includes key ocean variables: sea surface height, temperature, salinity, and currents, along with standardized metrics grounded in physical oceanography. Baseline comparisons with operational systems and state-of-the-art deep learning models are provided. All data, code, and evaluation protocols are openly available at https://github.com/mercator-ocean/oceanbench , establishing Ocean-Bench as a foundation for reproducible and rigorous research in data-driven ocean forecasting.

Data Driven Reconstruction of Upper Ocean Profiles for Improved State Estimation in the Philippine Sea

Despite significant advances in observational systems such as the global Argo array of autonomous profiling floats, the spatiotemporal coverage of subsurface ocean observations remains limited compared to the dense data provided by satellite platforms. This study develops a data‐driven framework to reconstruct synthetic profiles of upper ocean temperature and salinity by training a self‐attention‐based neural network with satellite‐derived sea surface height (SSH) and sea surface temperature anomalies, using 17 years of collocated Argo float measurements. Daily synthetic profiles for the upper 650 m of the Philippine Sea were generated for the entirety of 2010 and assimilated into a regional ocean model via 4D‐Var data assimilation. Results show overall improved effectiveness of state estimation when synthetic profiles are utilized. Diagnostic variables like temperature, salinity, SSH, horizontal velocity all show improvement. Synthetic profiles of subsurface temperature had an overall positive impact on SSH analysis and forecast, especially in regions east of the Luzon Strait and the southern domain influenced by the North Equatorial Current. In the vertical range of 150–600 m, the impact of synthetic profiles on various observations was promising, leading to substantial reductions in the analysis and forecast error.

RoughNet: Mapping Arctic Sea Ice Roughness Using Diffusion-Based Super-Resolution of Satellite Imagery

Accurate estimation of landfast sea ice roughness is critical for climate modeling and safe Arctic over-ice travel, yet existing approaches rely on costly airborne surveys or sparse in-situ measurements, limiting spatial coverage and operational scalability. Here we show that high-resolution sea ice topography can be reconstructed directly from optical satellite imagery using a conditional diffusion framework. Our approach, RoughNet, learns to map 10 m Sentinel-2 multispectral images to locally normalized 1 m surface elevation residual fields, enabling fine-scale roughness characterization from widely available satellite data. Trained on airborne LiDAR data from two Arctic regions and evaluated on an unseen third Arctic region, the model generalizes across diverse ice conditions and partially reproduces small-scale topographic structure. The best-performing model achieves an out-of-domain root mean squared error of 9 cm while preserving the statistical and spectral properties of the underlying roughness field. These results demonstrate that generative diffusion models can recover physically meaningful surface structure from optical imagery alone, providing a scalable pathway for high-resolution sea ice mapping and roughness estimation in data-sparse environments.

Deep Ocean Temperature from the Stratus Ocean Reference Station (85 °W, 20 °S), 2012-2025.

Long-term deep ocean temperature monitoring is crucial for understanding the ocean's role in climate variability and storage of heat in the deep ocean. Observation of the ocean surface is relatively accessible via both in-situ and remote sensing; however, continuous, high-temporal resolution, decade-long temperature records from abyssal depths face the technical challenges of sustained deep ocean deployments. The addition of calibrated, internally-recording temperature sensors to deep-ocean moorings not far from the sea floor provides a means of making high temporal resolution temperature observations. Quality controlling and merging records from successive mooring deployments results in a decade-long time series. Our work has been to optimize approaches for ensuring data quality and continuity in multi-year deep ocean temperature datasets. Here we show a comprehensive processing framework that yields 13 years (2012 to 2025) of continuous temperature measurements at approximately 4200 to 4500 meters depth from the Stratus Ocean Reference Station near 22 °S, 85 °W, 1500 km off the coast of Chile in the Southeast Pacific. Our framework incorporates timing checks, automated spike detection, systematic multi-sensor validation, statistical validation, human-in-the-loop quality control, and merging protocols. This framework establishes reproducible standards for processing long term oceanographic observations from multiple deployments. For the Stratus data set, the result is a unique, decade-long abyssal temperature record with quantified uncertainties that constitutes a benchmark time series for evaluating the realism of deep ocean temperature in models.