Ocean science, which delves into the oceans that are reservoirs of life and biodiversity, is of great significance given that oceans cover over 70% of our planet's surface. Recently, advances in Large Language Models (LLMs) have transformed the paradigm in science. Despite the success in other domains, current LLMs often fall short in catering to the needs of domain experts like oceanographers, and the potential of LLMs for ocean science is under-explored. The intrinsic reasons are the immense and intricate nature of ocean data as well as the necessity for higher granularity and richness in knowledge. To alleviate these issues, we introduce OceanGPT, the first-ever large language model in the ocean domain, which is expert in various ocean science tasks. We also propose OceanGPT, a novel framework to automatically obtain a large volume of ocean domain instruction data, which generates instructions based on multi-agent collaboration. Additionally, we construct the first oceanography benchmark, OceanBench, to evaluate the capabilities of LLMs in the ocean domain. Though comprehensive experiments, OceanGPT not only shows a higher level of knowledge expertise for oceans science tasks bu
We investigate the magnetic signature of oceanic circulation in Ganymede's subsurface ocean using kinematic induction modeling. Our approach couples zonal jet flows from rotating thermal convection simulations with magnetic field models incorporating Ganymede's internal dynamo and external contributions from Jupiter. We solve the induction equation in spherical geometry for deep-ocean (493 km) and shallow-ocean (287 km) scenarios with varying magnetic Reynolds numbers. Ocean flows generate a predominantly toroidal magnetic field through the omega-effect, with a weaker poloidal component pervading beyond the conductive ocean layer. For some, but not all, induction configurations, analysis of the time-averaged Lowes-Mauersberger spectra reveals that ocean-induced signals dominate at spherical harmonic degrees $\ell \geq 4$. Deep ocean scenarios with magnetic Reynolds numbers above unity produce surface magnetic signals up to 9 nT. Our results demonstrate that Ganymede's intrinsic magnetic field creates favorable conditions for detecting subsurface ocean dynamics, thus emphasizing the need for low-altitude orbits for the Juice probe.
Accurate ocean dynamics modeling is crucial for enhancing understanding of ocean circulation, predicting climate variability, and tackling challenges posed by climate change. Despite improvements in traditional numerical models, predicting global ocean variability over multi-year scales remains challenging. Here, we propose ORCA-DL (Oceanic Reliable foreCAst via Deep Learning), the first data-driven 3D ocean model for seasonal to decadal prediction of global ocean circulation. ORCA-DL accurately simulates three-dimensional ocean dynamics and outperforms state-of-the-art dynamical models in capturing extreme events, including El Niño-Southern Oscillation and upper ocean heatwaves. This demonstrates the high potential of data-driven models for efficient and accurate global ocean forecasting. Moreover, ORCA-DL stably emulates ocean dynamics at decadal timescales, demonstrating its potential even for skillful decadal predictions and climate projections.
Artificial intelligence has advanced global weather forecasting, outperforming traditional numerical models in both accuracy and computational efficiency. Nevertheless, extending predictions beyond subseasonal timescales requires the development of deep learning (DL)-based ocean-atmosphere coupled models that can realistically simulate complex oceanic responses to atmospheric forcing. This study presents KIST-Ocean, a DL-based global three-dimensional ocean general circulation model using a U-shaped visual attention adversarial network architecture. KIST-Ocean integrates partial convolution, adversarial training, and transfer learning to address coastal complexity and predictive distribution drift in auto-regressive models. Comprehensive evaluations confirmed the model's robust ocean predictive skill and efficiency. Moreover, it accurately captures realistic ocean response, such as Kelvin and Rossby wave propagation in the tropical Pacific, and vertical motions induced by cyclonic and anticyclonic wind stress, demonstrating its ability to represent key ocean-atmosphere coupling mechanisms underlying climate phenomena, including the El Nino-Southern Oscillation. These findings reinf
Latent heat flux is a primary pathway for ocean-atmosphere exchange of heat and moisture, yet the influence of sea surface temperature variability at fine scales ($\leq$ 100 km) on latent heat flux variability, particularly over the Southern Ocean, remains poorly understood. Here we quantify the scale-dependent drivers of latent heat flux (LHF) variability using a year-long, global, fully coupled ocean-atmosphere simulation with kilometer-scale resolution. Annual-mean LHF in eddy-rich regions reaches $\approx$ 215 W m$^{-2}$, approximately three times larger than in eddy-poor regions. Spectral analyses show that ocean mesoscale [$\mathcal{O}$(100 km)] and submesoscale [$\mathcal{O}$(1-10 km)] variability accounts for up to $\approx$ 80% of the total LHF variance in eddy-rich sectors, but as little as 10% in eddy-poor regions, and increases proportionally with eddy kinetic energy and sea surface temperature (SST) variance. We also find that strong submesoscale SST fronts ($\approx$ 5 $^\circ$C over 10 km) force a localized secondary circulation that extends well above the marine boundary layer into the mid-troposphere. Comparison with ERA5 shows that fine ocean scales, responsible f
Observational data suggest that the ice shell on Enceladus is thicker at the equator than at the pole, indicating an equator-to-pole ice flow. If the ice shell is in an equilibrium state, the mass transport of the ice flow must be balanced by the freezing and melting of the ice shell, which in turn is modulated by the ocean heat transport. Here we use a numerical ocean model to study the ice-ocean interaction and ocean circulation on Enceladus with different salinities. We find that salinity fundamentally determines the ocean stratification. A stratified layer forms in the low salinity ocean, affecting the ocean circulation and heat transport. However, in the absence of tidal heating in the ice shell, the ocean heat transport is found to always be towards lower latitudes, resulting in freezing at the poles, which cannot maintain the ice shell geometry against the equator-to-pole ice flow. The simulation results suggest that either the ice shell on Enceladus is not in an equilibrium state, or tidal dissipation in the ice shell is important in maintaining the ice shell geometry. The simulations also suggest that a positive feedback between cross-equatorial ocean heat transport and ic
AI emulators for forecasting have emerged as powerful tools that can outperform conventional numerical predictions. The next frontier is to build emulators for long climate simulations with skill across a range of spatiotemporal scales, a particularly important goal for the ocean. Our work builds a skillful global emulator of the ocean component of a state-of-the-art climate model. We emulate key ocean variables, sea surface height, horizontal velocities, temperature, and salinity, across their full depth. We use a modified ConvNeXt UNet architecture trained on multi-depth levels of ocean data. We show that the ocean emulator - Samudra - which exhibits no drift relative to the truth, can reproduce the depth structure of ocean variables and their interannual variability. Samudra is stable for centuries and 150 times faster than the original ocean model. Samudra struggles to capture the correct magnitude of the forcing trends and simultaneously remain stable, requiring further work.
Ocean forecasting is crucial for both scientific research and societal benefits. Currently, the most accurate forecasting systems are global ocean forecasting systems (GOFSs), which represent the ocean state variables (OSVs) as discrete grids and solve partial differential equations (PDEs) governing the transitions of oceanic state variables using numerical methods. However, GOFSs processes are computationally expensive and prone to cumulative errors. Recently, large artificial intelligence (AI)-based models significantly boosted forecasting speed and accuracy. Unfortunately, building a large AI ocean forecasting system that can be considered cross-spatiotemporal and air-sea coupled forecasts remains a significant challenge. Here, we introduce LangYa, a cross-spatiotemporal and air-sea coupled ocean forecasting system. Results demonstrate that the time embedding module in LangYa enables a single model to make forecasts with lead times ranging from 1 to 7 days. The air-sea coupled module effectively simulates air-sea interactions. The ocean self-attention module improves network stability and accelerates convergence during training, and the adaptive thermocline loss function improve
The scientific and technological revolution of the Internet of Things has begun in the area of oceanography. Historically, humans have observed the ocean from an external viewpoint in order to study it. In recent years, however, changes have occurred in the ocean, and laboratories have been built on the seafloor. Approximately 70.8% of the Earth's surface is covered by oceans and rivers. The Ocean of Things is expected to be important for disaster prevention, ocean-resource exploration, and underwater environmental monitoring. Unlike traditional wireless sensor networks, the Ocean Network has its own unique features, such as low reliability and narrow bandwidth. These features will be great challenges for the Ocean Network. Furthermore, the integration of the Ocean Network with artificial intelligence has become a topic of increasing interest for oceanology researchers. The Cognitive Ocean Network (CONet) will become the mainstream of future ocean science and engineering developments. In this article, we define the CONet. The contributions of the paper are as follows: (1) a CONet architecture is proposed and described in detail; (2) important and useful demonstration applications o
Titan's ice shell floats on top of a global ocean revealed by the large tidal Love number $k_2 = 0.616\pm0.067$ registered by Cassini. The Cassini observation exceeds the predicted $k_2$ by one order of magnitude in the absence of an ocean, and is 3-$σ$ away from the predicted $k_2$ if the ocean is pure water resting on top of a rigid ocean floor. Previous studies demonstrate that an ocean heavily enriched in salts (salinity $S\gtrsim200$ g/kg) can explain the 3-$σ$ signal in $k_2$. Here we revisit previous interpretations of Titan's large $k_2$ using simple physical arguments and propose a new interpretation based on the dynamic tidal response of a stably stratified ocean in resonance with eccentricity tides raised by Saturn. Our models include inertial effects from a full consideration of the Coriolis force and the radial stratification of the ocean, typically neglected or approximated elsewhere. The stratification of the ocean emerges from a salinity profile where salt concentration linearly increases with depth. We find multiple salinity profiles that lead to the $k_2$ required by Cassini. In contrast with previous interpretations that neglect stratification, resonant stratific
Motivated by the important role of the ocean in the Earth climate system, here we investigate possible scenarios of ocean circulations on exoplanets using a one-layer shallow water ocean model. Specifically, we investigate how planetary rotation rate, wind stress, fluid eddy viscosity and land structure (a closed basin vs. a reentrant channel) influence the pattern and strength of wind-driven ocean circulations. The meridional variation of the Coriolis force, arising from planetary rotation and the spheric shape of the planets, induces the western intensification of ocean circulations. Our simulations confirm that in a closed basin, changes of other factors contribute to only enhancing or weakening the ocean circulations (e.g., as wind stress decreases or fluid eddy viscosity increases, the ocean circulations weaken, and vice versa). In a reentrant channel, just as the Southern Ocean region on the Earth, the ocean pattern is characterized by zonal flows. In the quasi-linear case, the sensitivity of ocean circulations characteristics to these parameters is also interpreted using simple analytical models. This study is the preliminary step for exploring the possible ocean circulation
Recent field campaigns have consistently documented bottom-intensified mixing near the seafloor, suggesting diabatic downwelling in the abyssal ocean. This phenomenon appears to contradict with the mass balance of the abyssal ocean, where dense bottom water plunges into the region from the Antarctic side. Previous studies have sought to resolve this apparent paradox by proposing mixing-induced diabatic upwelling along bottom slopes. In contrast, this study offers an alternative perspective, highlighting the role of isopycnal displacement in the transient abyss. Motivated by emerging evidence of a cooling phase in the abyssal Indo-Pacific, likely linked to the last Little Ice Age, this study reinterprets the interior-downwelling paradox from the perspective of unsteady thermal states. Idealized numerical experiments were conducted to explore the abyssal overturning dynamics, with a focus on the behavior of advective, adiabatic, and diffusive overturning circulation streamfunctions in both cooling and warming scenarios. The results reveal that while the direction of diabatic overturning (upwelling or downwelling) depends on the transient state of the ocean, advective overturning circ
The ocean front has an important impact in many areas, it is meaningful to obtain accurate ocean front positioning, therefore, ocean front detection is a very important task. However, the traditional edge detection algorithm does not detect the weak edge information of the ocean front very well. In response to this problem, we collected relevant ocean front gradient images and found relevant experts to calibrate the ocean front data to obtain groundtruth, and proposed a weak edge identification nets(WEIN) for ocean front detection. Whether it is qualitative or quantitative, our methods perform best. The method uses a welltrained deep learning model to accurately extract the ocean front from the ocean front gradient image. The detection network is divided into multiple stages, and the final output is a multi-stage output image fusion. The method uses the stochastic gradient descent and the correlation loss function to obtain a good ocean front image output.
The development and evaluation of machine vision in underwater environments remains challenging, often relying on trial-and-error-based testing tailored to specific applications. This is partly due to the lack of controlled, ground-truthed testing environments that account for the optical challenges, such as color distortion from spectrally variant light attenuation, reduced contrast and blur from backscatter and volume scattering, and dynamic light patterns from natural or artificial illumination. Additionally, the appearance of ocean water in images varies significantly across regions, depths, and seasons. However, most machine vision evaluations are conducted under specific optical water types and imaging conditions, therefore often lack generalizability. Exhaustive testing across diverse open-water scenarios is technically impractical. To address this, we introduce the \textit{Optical Ocean Recipes}, a framework for creating realistic datasets under controlled underwater conditions. Unlike synthetic or open-water data, these recipes, using calibrated color and scattering additives, enable repeatable and controlled testing of the impact of water composition on image appearance.
The current explosion in machine learning for climate has led to skilled, computationally cheap emulators for the atmosphere. However, the research for ocean emulators remains nascent despite the large potential for accelerating coupled climate simulations and improving ocean forecasts on all timescales. There are several fundamental questions to address that can facilitate the creation of ocean emulators. Here we focus on two questions: 1) the role of the atmosphere in improving the extended skill of the emulator and 2) the representation of variables with distinct timescales (e.g., velocity and temperature) in the design of any emulator. In tackling these questions, we show stable prediction of surface fields for over 8 years, training and testing on data from a high-resolution coupled climate model, using results from four regions of the globe. Our work lays out a set of physically motivated guidelines for building ocean climate emulators.
Crystallization of the lunar magma ocean yielded a chemically unique liquid residuum named KREEP. This component is expressed as a large patch on the near side of the Moon, and a possible smaller patch in the northwest portion of the Moon's South Pole-Aitken basin on the far side. Thermal models estimate that the crystallization of the lunar magma ocean (LMO) could have spanned from 10 and 200 Myr, while studies of radioactive decay systems have yielded inconsistent ages for the completion of LMO crystallization covering over 160 Myr. Here, we show that the Moon achieved over 99 percent crystallization at 4429+/-76 Myr, indicating a lunar formation age of 4450 Myr or possibly older. Using the 176Lu-176Hf decay system (t1/2=37 Gyr), we found that the initial 176Hf/177Hf ratios of lunar zircons with varied U-Pb ages are consistent with their crystallization from a KREEP-rich reservoir with a consistently low 176Lu/177Hf ratio of 0.0167 that emerged ~140 Myr after solar system formation. The previously proposed younger model age of 4.33 Ga for the source of mare basalts (240 Myr after solar system formation) might reflect the timing of a large impact. Our results demonstrate that luna
Enceladus is believed to have a saltwater global ocean with a mean depth of at least 30~km, heated from below at the ocean-core interface and cooled at the top, where the ocean loses heat to the icy lithosphere above. This scenario suggests an important role for vertical convection to influence the interior properties and circulation of Enceladus' ocean. Additionally, the ice shell that encompasses the ocean has dramatic meridional thickness variations that, in steady state, must be sustained against processes acting to remove these ice thickness anomalies. One mechanism that would maintain variations in the ice shell thickness involves spatially-separated regions of freezing and melting at the ocean-ice interface. Here, we use an idealized, dynamical ocean model forced by an observationally-guided density forcing at the ocean-ice interface to argue that Enceladus' interior ocean should support a meridional overturning circulation. This circulation establishes an interior density structure that is more complex than in studies that have focused only on convection, including a shallow freshwater lens in the polar regions. Spatially-separated sites of ice formation and melt enable Enc
The circulation in Europa's ocean determines the degree of thermal, mechanical and chemical coupling between the ice shell and the silicate mantle. Using global direct numerical simulations, we investigate the effect of heterogeneous tidal heating in the silicate mantle on rotating thermal convection in the ocean and its consequences on ice shell thickness. Under the assumption of no salinity or ocean-ice shell feedbacks, we show that convection largely transposes the latitudinal variations of tidal heating from the seafloor to the ice, leading to a higher oceanic heat flux in polar regions. Longitudinal variations are efficiently transferred when boundary-driven thermal winds develop, but are reduced in the presence of strong zonal flows and may vanish in planetary regimes. If spatially homogeneous radiogenic heating is dominant in the silicate mantle, the ocean's contribution to ice shell thickness variations is negligible compared to tidal heating within the ice. If tidal heating is instead dominant in the mantle, the situation is reversed and the ocean controls the pole-to-equator thickness contrast, as well as possible longitudinal variations.
The ice shell and subsurface ocean on icy worlds are strongly coupled together -- heat and salinity flux from the ice shell induced by the ice thickness gradient drives circulation in the ocean, and in turn, the heat transport by ocean circulation shapes the ice shell. Since measurements in the near future are likely to remain constrained to above the ice shell, understanding this ocean-ice interaction is crucial. Using an ocean box model and a series of experiments simulating the 2D ocean circulation, we find that large icy moons with strong gravity tend to have stronger ocean heat transport under the same ice-shell topography. As a result, the equilibrium ice shell geometry is expected to be flatter on moons with larger size, and vice versa. This finding is broadly consistent with the observed ice shell geometry for Enceladus and Europa.
Globally ice-covered oceans have been found on multiple moons in the solar system and may also have been a feature of Earth's past. However, relatively little is understood about the dynamics of these ice-covered oceans, which affect not only the physical environment but also any potential life and its detectability. A number of studies have simulated the circulation of icy-world oceans, but have come to seemingly widely different conclusions. To better understand and narrow down these diverging results, we discuss energetic constraints for the circulation on ice-covered oceans, focusing in particular on Snowball Earth, Europa, and Enceladus. Energy input that can drive ocean circulation on ice-covered bodies can be associated with heat and salt fluxes at the boundaries as well as ocean tides and librations. We show that heating from the solid core balanced by heat loss through the ice sheet can drive an ocean circulation, but the resulting flows would be relatively weak and strongly affected by rotation. Salt fluxes associated with freezing and melting at the ice sheet boundary are unlikely to energetically drive a circulation, although they can shape the large-scale circulation w