Ocean & Sea Ice¶
-
Lazy Diffusion: Mitigating spectral collapse in generative diffusion-based stable autoregressive emulation of turbulent flows¶
Turbulent flows posses broadband, power-law spectra in which multiscale interactions couple high-wavenumber fluctuations to large-scale dynamics. Although diffusion-based generative models offer a...Turbulent flows posses broadband, power-law spectra in which multiscale interactions couple high-wavenumber fluctuations to large-scale dynamics. Although diffusion-based generative models offer a principled probabilistic forecasting framework, we show that standard DDPMs induce a fundamental spectral collapse: a Fourier-space analysis of the forward SDE reveals a closed-form, mode-wise signal-to-noise ratio (SNR) that decays monotonically in wavenumber, \(|k|\) for spectra \(S(k)\!\propto\!|k|^{-λ}\), rendering high-wavenumber modes indistinguishable from noise and producing an intrinsic spectral bias. We reinterpret the noise schedule as a spectral regularizer and introduce power-law schedules \(β(τ)\!\propto\!τ^γ\) that preserve fine-scale structure deeper into diffusion time, along with Lazy Diffusion, a one-step distillation method that leverages the learned score geometry to bypass long reverse-time trajectories and prevent high-\(k\) degradation. Applied to high-Reynolds-number 2D Kolmogorov turbulence and \(1/12^\circ\) Gulf of Mexico ocean reanalysis, these methods resolve spectral collapse, stabilize long-horizon autoregression, and restore physically realistic inertial-range scaling. Together, they show that naïve Gaussian scheduling is structurally incompatible with power-law physics and that physics-aware diffusion processes can yield accurate, efficient, and fully probabilistic surrogates for multiscale dynamical systems. more
-
CLIMATEAGENT: Multi-Agent Orchestration for Complex Climate Data Science Workflows¶
Climate science demands automated workflows to transform comprehensive questions into data-driven statements across massive, heterogeneous datasets. However, generic LLM agents and static scripting...Climate science demands automated workflows to transform comprehensive questions into data-driven statements across massive, heterogeneous datasets. However, generic LLM agents and static scripting pipelines lack climate-specific context and flexibility, thus, perform poorly in practice. We present ClimateAgent, an autonomous multi-agent framework that orchestrates end-to-end climate data analytic workflows. ClimateAgent decomposes user questions into executable sub-tasks coordinated by an Orchestrate-Agent and a Plan-Agent; acquires data via specialized Data-Agents that dynamically introspect APIs to synthesize robust download scripts; and completes analysis and reporting with a Coding-Agent that generates Python code, visualizations, and a final report with a built-in self-correction loop. To enable systematic evaluation, we introduce Climate-Agent-Bench-85, a benchmark of 85 real-world tasks spanning atmospheric rivers, drought, extreme precipitation, heat waves, sea surface temperature, and tropical cyclones. On Climate-Agent-Bench-85, ClimateAgent achieves 100% task completion and a report quality score of 8.32, outperforming GitHub-Copilot (6.27) and a GPT-5 baseline (3.26). These results demonstrate that our multi-agent orchestration with dynamic API awareness and self-correcting execution substantially advances reliable, end-to-end automation for climate science analytic tasks. more
-
The Role of Deep Mesoscale Eddies in Ensemble Forecast Performance¶
Present forecasting efforts rely on assimilation of observational data captured in the upper ocean (< 1000 m depth). These observations constrain the upper ocean and minimally influence the deep...Present forecasting efforts rely on assimilation of observational data captured in the upper ocean (< 1000 m depth). These observations constrain the upper ocean and minimally influence the deep ocean. Nevertheless, development of the full water column circulation critically depends upon the dynamical interactions between upper and deep fields. Forecasts demonstrate that the initialization of the deep field is influential for the development and evolution of the surface in the forecast. Deep initial conditions that better agree with observations have lower upper ocean uncertainty as the forecast progresses. Here, best and worst ensemble members in two 92-day forecasts are identified and contrasted in order to determine how the deep ocean differs between these groups. The forecasts cover the duration of the Loop Current Eddy Thor separation event, which coincides with available deep observations in the Gulf. Model member performance is assessed by comparing surface variables against verifying analysis and satellite altimeter data during the forecast time-period. Deep cyclonic and anticyclonic features are reviewed, and compared against deep observations, indicating subtle differences in locations of deep eddies at relevant times. These results highlight both the importance of deep circulation in the dynamics of the Loop Current system and more broadly motivate efforts to assimilate deep observations to better constrain the deep initial fields and improve surface predictions. more
-
SSTODE: Ocean-Atmosphere Physics-Informed Neural ODEs for Sea Surface Temperature Prediction¶
Sea Surface Temperature (SST) is crucial for understanding upper-ocean thermal dynamics and ocean-atmosphere interactions, which have profound economic and social impacts. While data-driven models...Sea Surface Temperature (SST) is crucial for understanding upper-ocean thermal dynamics and ocean-atmosphere interactions, which have profound economic and social impacts. While data-driven models show promise in SST prediction, their black-box nature often limits interpretability and overlooks key physical processes. Recently, physics-informed neural networks have been gaining momentum but struggle with complex ocean-atmosphere dynamics due to 1) inadequate characterization of seawater movement (e.g., coastal upwelling) and 2) insufficient integration of external SST drivers (e.g., turbulent heat fluxes). To address these challenges, we propose SSTODE, a physics-informed Neural Ordinary Differential Equations (Neural ODEs) framework for SST prediction. First, we derive ODEs from fluid transport principles, incorporating both advection and diffusion to model ocean spatiotemporal dynamics. Through variational optimization, we recover a latent velocity field that explicitly governs the temporal dynamics of SST. Building upon ODE, we introduce an Energy Exchanges Integrator (EEI)-inspired by ocean heat budget equations-to account for external forcing factors. Thus, the variations in the components of these factors provide deeper insights into SST dynamics. Extensive experiments demonstrate that SSTODE achieves state-of-the-art performances in global and regional SST forecasting benchmarks. Furthermore, SSTODE visually reveals the impact of advection dynamics, thermal diffusion patterns, and diurnal heating-cooling cycles on SST evolution. These findings demonstrate the model's interpretability and physical consistency. more
-
OceanAI: A Conversational Platform for Accurate, Transparent, Near-Real-Time Oceanographic Insights¶
Artificial intelligence is transforming the sciences, yet general conversational AI systems often generate unverified "hallucinations" undermining scientific rigor. We present OceanAI, a...Artificial intelligence is transforming the sciences, yet general conversational AI systems often generate unverified "hallucinations" undermining scientific rigor. We present OceanAI, a conversational platform that integrates the natural-language fluency of open-source large language models (LLMs) with real-time, parameterized access to authoritative oceanographic data streams hosted by the National Oceanic and Atmospheric Administration (NOAA). Each query such as "What was Boston Harbor's highest water level in 2024?" triggers real-time API calls that identify, parse, and synthesize relevant datasets into reproducible natural-language responses and data visualizations. In a blind comparison with three widely used AI chat-interface products, only OceanAI produced NOAA-sourced values with original data references; others either declined to answer or provided unsupported results. Designed for extensibility, OceanAI connects to multiple NOAA data products and variables, supporting applications in marine hazard forecasting, ecosystem assessment, and water-quality monitoring. By grounding outputs and verifiable observations, OceanAI advances transparency, reproducibility, and trust, offering a scalable framework for AI-enabled decision support within the oceans. A public demonstration is available at https://oceanai.ai4ocean.xyz. more
-
Sensitivity Analysis for Climate Science with Generative Flow Models¶
Sensitivity analysis is a cornerstone of climate science, essential for understanding phenomena ranging from storm intensity to long-term climate feedbacks. However, computing these sensitivities...Sensitivity analysis is a cornerstone of climate science, essential for understanding phenomena ranging from storm intensity to long-term climate feedbacks. However, computing these sensitivities using traditional physical models is often prohibitively expensive in terms of both computation and development time. While modern AI-based generative models are orders of magnitude faster to evaluate, computing sensitivities with them remains a significant bottleneck. This work addresses this challenge by applying the adjoint state method for calculating gradients in generative flow models. We apply this method to the cBottle generative model, trained on ERA5 and ICON data, to perform sensitivity analysis of any atmospheric variable with respect to sea surface temperatures. We quantitatively validate the computed sensitivities against the model's own outputs. Our results provide initial evidence that this approach can produce reliable gradients, reducing the computational cost of sensitivity analysis from weeks on a supercomputer with a physical model to hours on a GPU, thereby simplifying a critical workflow in climate science. The code can be found at https://github.com/Kwartzl8/cbottle_adjoint_sensitivity. more
-
Leveraging an Atmospheric Foundational Model for Subregional Sea Surface Temperature Forecasting¶
The accurate prediction of oceanographic variables is crucial for understanding climate change, managing marine resources, and optimizing maritime activities. Traditional ocean forecasting relies on...The accurate prediction of oceanographic variables is crucial for understanding climate change, managing marine resources, and optimizing maritime activities. Traditional ocean forecasting relies on numerical models; however, these approaches face limitations in terms of computational cost and scalability. In this study, we adapt Aurora, a foundational deep learning model originally designed for atmospheric forecasting, to predict sea surface temperature (SST) in the Canary Upwelling System. By fine-tuning this model with high-resolution oceanographic reanalysis data, we demonstrate its ability to capture complex spatiotemporal patterns while reducing computational demands. Our methodology involves a staged fine-tuning process, incorporating latitude-weighted error metrics and optimizing hyperparameters for efficient learning. The experimental results show that the model achieves a low RMSE of 0.119K, maintaining high anomaly correlation coefficients (ACC \(\approx 0.997\)). The model successfully reproduces large-scale SST structures but faces challenges in capturing finer details in coastal regions. This work contributes to the field of data-driven ocean forecasting by demonstrating the feasibility of using deep learning models pre-trained in different domains for oceanic applications. Future improvements include integrating additional oceanographic variables, increasing spatial resolution, and exploring physics-informed neural networks to enhance interpretability and understanding. These advancements can improve climate modeling and ocean prediction accuracy, supporting decision-making in environmental and economic sectors. more
-
Principled Operator Learning in Ocean Dynamics: The Role of Temporal Structure¶
Neural operators are becoming the default tools to learn solutions to governing partial differential equations (PDEs) in weather and ocean forecasting applications. Despite early promising...Neural operators are becoming the default tools to learn solutions to governing partial differential equations (PDEs) in weather and ocean forecasting applications. Despite early promising achievements, significant challenges remain, including long-term prediction stability and adherence to physical laws, particularly for high-frequency processes. In this paper, we take a step toward addressing these challenges in high-resolution ocean prediction by incorporating temporal Fourier modes, demonstrating how this modification enhances physical fidelity. This study compares the standard Fourier Neural Operator (FNO) with its variant, FNOtD, which has been modified to internalize the dispersion relation while learning the solution operator for ocean PDEs. The results demonstrate that entangling space and time in the training of integral kernels enables the model to capture multiscale wave propagation and effectively learn ocean dynamics. FNOtD substantially improves long-term prediction stability and consistency with underlying physical dynamics in challenging high-frequency settings compared to the standard FNO. It also provides competitive predictive skill relative to a state-of-the-art numerical ocean model, while requiring significantly lower computational cost. more
-
Down-scale marine hydrodynamic analysis at the Norwegian coast -- the NORA-SARAH open framework¶
Offshore wave studies often assume Gaussian processes and homogeneous wave fields. However, as waves approach the shoreline, complex coastal topo-bathymetry induces transformations such as shoaling,...Offshore wave studies often assume Gaussian processes and homogeneous wave fields. However, as waves approach the shoreline, complex coastal topo-bathymetry induces transformations such as shoaling, refraction, diffraction, reflection, and breaking, leading to increased nonlinearity and site-specific wave characteristics. This complexity necessitates detailed site-specific studies for coastal infrastructure design and blue economy planning. This work presents a downscaling procedure for analyzing wave-structure interactions from offshore metocean conditions. The open-access NORA3 and NORA10EI hindcast databases define offshore sea states, which are propagated to nearshore regions using the phase-averaged wave model SWAN. The outputs inform phase-resolving simulations with the fully nonlinear potential flow solver REEF3D::FNPF, incorporating an Arbitrary Eulerian-Lagrangian (ALE) method to compute wave forces via Morisons formulation and to screen for extreme events. Extreme wave loads are further examined using the fully viscous Navier-Stokes solver REEF3D::CFD. A one-way hydrodynamic coupling (HDC) between the potential flow and viscous solvers ensures accurate information transfer. The proposed NORA-SARAH framework, integrating NORA databases with SWAN, REEF3D, ALE, and HDC, offers a robust approach for complex coastal environments. A case study in Southern Norway demonstrates its advantages over traditional significant wave height (Hs)-based or phase-averaged modeling practices, highlighting the necessity of this downscaling method. more
-
Data-Driven Reconstruction of Significant Wave Heights from Sparse Observations¶
Reconstructing high-resolution regional significant wave height fields from sparse and uneven buoy observations remains a core challenge for ocean monitoring and risk-aware operations. We introduce...Reconstructing high-resolution regional significant wave height fields from sparse and uneven buoy observations remains a core challenge for ocean monitoring and risk-aware operations. We introduce AUWave, a hybrid deep learning framework that fuses a station-wise sequence encoder (MLP) with a multi-scale U-Net enhanced by a bottleneck self-attention layer to recover 32\(\times\)32 regional SWH fields. A systematic Bayesian hyperparameter search with Optuna identifies the learning rate as the dominant driver of generalization, followed by the scheduler decay and the latent dimension. Using NDBC buoy observations and ERA5 reanalysis over the Hawaii region, AUWave attains a minimum validation loss of 0.043285 and a slightly right-skewed RMSE distribution. Spatial errors are lowest near observation sites and increase with distance, reflecting identifiability limits under sparse sampling. Sensitivity experiments show that AUWave consistently outperforms a representative baseline in data-richer configurations, while the baseline is only marginally competitive in the most underdetermined single-buoy cases. The architecture's multi-scale and attention components translate into accuracy gains when minimal but non-trivial spatial anchoring is available. Error maps and buoy ablations reveal key anchor stations whose removal disproportionately degrades performance, offering actionable guidance for network design. AUWave provides a scalable pathway for gap filling, high-resolution priors for data assimilation, and contingency reconstruction. more
-
Climate-Adaptive and Cascade-Constrained Machine Learning Prediction for Sea Surface Height under Greenhouse Warming¶
Machine learning (ML) has achieved remarkable success in climate and marine science. Given that greenhouse warming fundamentally reshapes ocean conditions such as stratification, circulation patterns...Machine learning (ML) has achieved remarkable success in climate and marine science. Given that greenhouse warming fundamentally reshapes ocean conditions such as stratification, circulation patterns and eddy activity, evaluating the climate adaptability of the ML models is crucial. While physical constraints have been shown to enhance the performance of ML models, kinetic energy (KE) cascade has not been used as a constraint despite its importance in regulating multi-scale ocean motions. Here we develop two sea surface height (SSH) prediction models (with and without KE cascade constraint) and quantify their climate adaptability at the Kuroshio Extension. Both models exhibit only slight performance degradation under greenhouse warming conditions. Incorporating the KE cascade as a physical constraint significantly improves the model performance, reducing eddy kinetic energy errors by 14.7% in the present climate and 15.9% under greenhouse warming. Additional validations using satellite observations and in the Gulf Stream region further confirm the robustness of the proposed models. Compared with the KE spectrum constraint, both constraints improve the cross-scale transfer and spectrum of KE, but the KE cascade constraint yields larger improvements in the cross-scale transfer. This work presents the first application of the KE cascade as a physical constraint for ML-based ocean state prediction and demonstrates its robust adaptability across climates, offering guidance for the further development of global ML models for both present and future conditions. more
-
A data-driven global ocean forecasting model with sub-daily and eddy-resolving resolution¶
High-fidelity ocean forecasting at high spatial and temporal resolution is essential for capturing fine-scale dynamical features, with profound implications for hazard prediction, maritime...High-fidelity ocean forecasting at high spatial and temporal resolution is essential for capturing fine-scale dynamical features, with profound implications for hazard prediction, maritime navigation, and sustainable ocean management. While conventional numerical models can generate sub-daily, eddy-resolving forecasts, they demand substantial computational resources and often struggle to maintain predictive skill at such fine scales. Data-driven models offer a promising alternative with significantly higher computational efficiency; however, most are constrained to daily outputs and show a rapid decay in accuracy when extended to sub-daily timescales. Here, we introduce TianHai, the first-of-its-kind global data-driven 6-hour forecasting model, which delivers predictions at 1/12° eddy-resolving resolution with a vertical extent down to 1,500 m. A key feature of TianHai is the integration of atmospheric forcings through FuXi-Atmosphere, a data-driven atmospheric forecasting system, which enables the explicit representation of air-sea coupling effects. Unlike conventional approaches, TianHai does not rely on numerical atmospheric models or external meteorological forecasts, making it a fully data-driven framework for coupled prediction. Benchmark experiments demonstrate that TianHai delivers state-of-the-art performance in forecasting temperature and salinity profiles, zonal and meridional currents, sea surface temperature, and sea level anomalies for lead times ranging from 1 to 10 days. more
-
Artificial neural networks ensemble methodology to predict significant wave height¶
The forecast of wave variables are important for several applications that depend on a better description of the ocean state. Due to the chaotic behaviour of the differential equations which model...The forecast of wave variables are important for several applications that depend on a better description of the ocean state. Due to the chaotic behaviour of the differential equations which model this problem, a well know strategy to overcome the difficulties is basically to run several simulations, by for instance, varying the initial condition, and averaging the result of each of these, creating an ensemble. Moreover, in the last few years, considering the amount of available data and the computational power increase, machine learning algorithms have been applied as surrogate to traditional numerical models, yielding comparative or better results. In this work, we present a methodology to create an ensemble of different artificial neural networks architectures, namely, MLP, RNN, LSTM, CNN and a hybrid CNN-LSTM, which aims to predict significant wave height on six different locations in the Brazilian coast. The networks are trained using NOAA's numerical reforecast data and target the residual between observational data and the numerical model output. A new strategy to create the training and target datasets is demonstrated. Results show that our framework is capable of producing high efficient forecast, with an average accuracy of \(80\%\), that can achieve up to \(88\%\) in the best case scenario, which means \(5\%\) reduction in error metrics if compared to NOAA's numerical model, and a increasingly reduction of computational cost. more
-
SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulators¶
Traditional numerical global climate models simulate the full Earth system by exchanging boundary conditions between separate simulators of the atmosphere, ocean, sea ice, land surface, and other...Traditional numerical global climate models simulate the full Earth system by exchanging boundary conditions between separate simulators of the atmosphere, ocean, sea ice, land surface, and other geophysical processes. This paradigm allows for distributed development of individual components within a common framework, unified by a coupler that handles translation between realms via spatial or temporal alignment and flux exchange. Following a similar approach adapted for machine learning-based emulators, we present SamudrACE: a coupled global climate model emulator which produces centuries-long simulations at 1-degree horizontal, 6-hourly atmospheric, and 5-daily oceanic resolution, with 145 2D fields spanning 8 atmospheric and 19 oceanic vertical levels, plus sea ice, surface, and top-of-atmosphere variables. SamudrACE is highly stable and has low climate biases comparable to those of its components with prescribed boundary forcing, with realistic variability in coupled climate phenomena such as ENSO that is not possible to simulate in uncoupled mode. more
-
Detecting extreme event-driven causality¶
The occurrence of some extreme events (such as marine heatwaves or exceptional circulations) can cause other extreme events (such as heatwave, drought and flood). These concurrent extreme events have...The occurrence of some extreme events (such as marine heatwaves or exceptional circulations) can cause other extreme events (such as heatwave, drought and flood). These concurrent extreme events have a great impact on environment and human health. However, how to detect and quantify the causes and impacts of these extreme events by a data-driven way is still unsolved. In this study, the dynamic system method is extended to develop a method for detecting the causality between extreme events. Taking the coupled Lorenz-Lorenz systems with extreme event-driven coupling as an example, it is demonstrated that this proposed detecting method is able to capture the extreme event-driven causality, with even better causality detecting performance between concurrent extreme events. Comparison among three kinds of measured series, full measurements outperform partial ones in event-to-event causality detecting. The successful applicability of our proposed approach in Walker circulation phenomenon indicates that our method contributes a novel way to the study of causal inference in complex systems. This method offers valuable insights into multi-scale, nonlinear dynamics, particularly in uncovering associations among extreme events. more
-
MedFormer: a data-driven model for forecasting the Mediterranean Sea¶
Accurate ocean forecasting is essential for supporting a wide range of marine applications. Recent advances in artificial intelligence have highlighted the potential of data-driven models to...Accurate ocean forecasting is essential for supporting a wide range of marine applications. Recent advances in artificial intelligence have highlighted the potential of data-driven models to outperform traditional numerical approaches, particularly in atmospheric weather forecasting. However, extending these methods to ocean systems remains challenging due to their inherently slower dynamics and complex boundary conditions. In this work, we present MedFormer, a fully data-driven deep learning model specifically designed for medium-range ocean forecasting in the Mediterranean Sea. MedFormer is based on a U-Net architecture augmented with 3D attention mechanisms and operates at a high horizontal resolution of 1/24°. The model is trained on 20 years of daily ocean reanalysis data and fine-tuned with high-resolution operational analyses. It generates 9-day forecasts using an autoregressive strategy. The model leverages both historical ocean states and atmospheric forcings, making it well-suited for operational use. We benchmark MedFormer against the state-of-the-art Mediterranean Forecasting System (MedFS), developed at Euro-Mediterranean Center on Climate Change (CMCC), using both analysis data and independent observations. The forecast skills, evaluated with the Root Mean Squared Difference and the Anomaly Correlation Coefficient, indicate that MedFormer consistently outperforms MedFS across key 3D ocean variables. These findings underscore the potential of data-driven approaches like MedFormer to complement, or even surpass, traditional numerical ocean forecasting systems in both accuracy and computational efficiency. more
-
DiffTopo: Solver in the Loop for Inverse Topography via Condition Diffusion Generation¶
Inferring seabed topography from wave height observations is fundamental to tsunami hazard assessment, coastal planning, and large scale ocean circulation modeling. Classical inversion models...Inferring seabed topography from wave height observations is fundamental to tsunami hazard assessment, coastal planning, and large scale ocean circulation modeling. Classical inversion models typically rely on direct sensing or optimization based schemes that must contend with the strongly nonlinear coupling between free surface dynamics and topography. However, data driven approaches are capable of tackling strongly nonlinear problems by learning the underlying data distributions. This study introduces DiffTopo, a conditional diffusion model that reconstructs topography from surface wave field data governed by shallow water equations. Leveraging classifier free guidance, DiffTopo not only generates a series of solutions but also applies a thresholding mechanism that ensures, via the solver, the validation results are physically plausible. This study evaluates both observed wave fields and three distinct topography configurations, demonstrating that DiffTopo exhibits robust generalization and remains consistent with the shallow water equations even under full observations. These results underscore the potential of diffusion based generative modeling for addressing ill posed inverse problems in geophysics. more
-
Ensembles of Neural Surrogates for Parametric Sensitivity in Ocean Modeling¶
Accurate simulations of the oceans are crucial in understanding the Earth system. Despite their efficiency, simulations at lower resolutions must rely on various uncertain parameterizations to...Accurate simulations of the oceans are crucial in understanding the Earth system. Despite their efficiency, simulations at lower resolutions must rely on various uncertain parameterizations to account for unresolved processes. However, model sensitivity to parameterizations is difficult to quantify, making it challenging to tune these parameterizations to reproduce observations. Deep learning surrogates have shown promise for efficient computation of the parametric sensitivities in the form of partial derivatives, but their reliability is difficult to evaluate without ground truth derivatives. In this work, we leverage large-scale hyperparameter search and ensemble learning to improve both forward predictions, autoregressive rollout, and backward adjoint sensitivity estimation. Particularly, the ensemble method provides epistemic uncertainty of function value predictions and their derivatives, providing improved reliability of the neural surrogates in decision making. more
-
Generative AI models capture realistic sea-ice evolution from days to decades¶
Sea ice plays an important role in stabilising the Earth system. Yet, representing its dynamics remains a major challenge for models, as the underlying processes are scale-invariant and highly...Sea ice plays an important role in stabilising the Earth system. Yet, representing its dynamics remains a major challenge for models, as the underlying processes are scale-invariant and highly anisotropic. This poses a dilemma: physics-based models that faithfully reproduce the observed dynamics are computationally costly, while efficient AI models sacrifice realism. Here, to resolve this dilemma, we introduce GenSIM, the first generative AI model to predict the evolution of the full Arctic sea-ice state at 12-hour increments. Trained for sub-daily forecasting on 20 years of sea-ice-ocean simulation data, GenSIM makes realistic predictions for 30 years, while reproducing the dynamical properties of sea ice with its leads and ridges and capturing long-term trends in the sea-ice volume. Notably, although solely driven by atmospheric reanalysis, GenSIM implicitly learns hidden signatures of multi-year ice-ocean interaction. Therefore, generative AI can extrapolate from sub-daily forecasts to decadal simulations, while retaining physical consistency. more
-
Knowledge-guided machine learning for disentangling Pacific sea surface temperature variability across timescales¶
Global weather patterns and regimes are heavily influenced by the dominant modes of Pacific sea surface temperature (SST) variability, including the El Niño-Southern Oscillation (ENSO), Tropical...Global weather patterns and regimes are heavily influenced by the dominant modes of Pacific sea surface temperature (SST) variability, including the El Niño-Southern Oscillation (ENSO), Tropical Pacific Decadal Variability (TPDV), North Pacific Meridional Mode (NPMM), and the Pacific Decadal Oscillation (PDO). However, separating these modes of variability remains challenging due to their spatial overlap and possible nonlinear coupling, which violates the assumptions of traditional linear methods. We develop a Knowledge-Guided AutoEncoder (KGAE) that uses spectral constraints to identify physically interpretable modes, without the need for predefined temporal filters or thresholds. The KGAE separates ENSO-like modes on 2- and 3-7-year timescales and a decadal mode with characteristics reminiscent of the PDO and the NPMM, each with distinct spatial patterns. We demonstrate that the decadal mode modulates ENSO diversity (central Pacific versus eastern Pacific), and that a quasibiennial mode leads and follows the interannual mode, suggesting a role in ENSO onset and decay. When applied to climate model output, KGAEs reveal model-specific biases in ENSO diversity and seasonal timing. Finally, residual training isolates a primarily equatorial decadal mode, which may be a component of TPDV-related decadal variability, likely originating from advection linked to upwelling near the Galápagos Islands and the South Equatorial Current. Our results highlight how machine learning can uncover physically meaningful modes of Earth system variability and improve the representation and evaluation of variability across models and timescales. more
-
Sparsity-Promoting Dynamic Mode Decomposition Applied to Sea Surface Temperature Fields¶
In this paper, we leverage Koopman mode decomposition to analyze the nonlinear and high-dimensional climate systems acting on the observed data space. The dynamics of atmospheric systems are assumed...In this paper, we leverage Koopman mode decomposition to analyze the nonlinear and high-dimensional climate systems acting on the observed data space. The dynamics of atmospheric systems are assumed to be equation-free, with the linear evolution of observables derived from measured historical long-term time-series data snapshots, such as monthly sea surface temperature records, to construct a purely data-driven climate dynamics. In particular, sparsity-promoting dynamic mode decomposition is exploited to extract the dominant spatial and temporal modes, which are among the most significant coherent structures underlying climate variability, enabling a more efficient, interpretable, and low-dimensional representation of the system dynamics. We hope that the combined use of Koopman modes and sparsity-promoting techniques will provide insights into the significant climate modes, enabling reduced-order modeling of the climate system and offering a potential framework for predicting and controlling weather and climate variability. more
-
IDRIFTNET: Physics-Driven Spatiotemporal Deep Learning for Iceberg Drift Forecasting¶
Drifting icebergs in the polar oceans play a key role in the Earth's climate system, impacting freshwater fluxes into the ocean and regional ecosystems while also posing a challenge to polar...Drifting icebergs in the polar oceans play a key role in the Earth's climate system, impacting freshwater fluxes into the ocean and regional ecosystems while also posing a challenge to polar navigation. However, accurately forecasting iceberg trajectories remains a formidable challenge, primarily due to the scarcity of spatiotemporal data and the complex, nonlinear nature of iceberg motion, which is also impacted by environmental variables. The iceberg motion is influenced by multiple dynamic environmental factors, creating a highly variable system that makes trajectory identification complex. These limitations hinder the ability of deep learning models to effectively capture the underlying dynamics and provide reliable predictive outcomes. To address these challenges, we propose a hybrid IDRIFTNET model, a physics-driven deep learning model that combines an analytical formulation of iceberg drift physics, with an augmented residual learning model. The model learns the pattern of mismatch between the analytical solution and ground-truth observations, which is combined with a rotate-augmented spectral neural network that captures both global and local patterns from the data to forecast future iceberg drift positions. We compare IDRIFTNET model performance with state-of-the-art models on two Antarctic icebergs: A23A and B22A. Our findings demonstrate that IDRIFTNET outperforms other models by achieving a lower Final Displacement Error (FDE) and Average Displacement Error (ADE) across a variety of time points. These results highlight IDRIFTNET's effectiveness in capturing the complex, nonlinear drift of icebergs for forecasting iceberg trajectories under limited data and dynamic environmental conditions. more
-
Machine learning-based correlation analysis of decadal cyclone intensity with sea surface temperature: data and tutorial¶
The rising number of extreme climate events in the past decades has motivated the need for a thorough consideration of tropical cyclone genesis and intensity, given the sea-surface temperature (SST)....The rising number of extreme climate events in the past decades has motivated the need for a thorough consideration of tropical cyclone genesis and intensity, given the sea-surface temperature (SST). In this paper, we present an analysis of the relationship between the increasing global SST with cyclone genesis using linear regression machine learning models. We extract and curate a dataset of tropical cyclones across selected ocean basins with their associated SST over the past 40 years. We provide correlation analysis using linear regression and visualisation strategies. Our preliminary results show a strong positive correlation between SST and high wind speed across selected ocean basins via linear regression and machine learning models. Our dataset and available open-source code offer a novel perspective for the investigation of the genesis and intensity of tropical cyclones. Alongside the time and position of each cyclone, we also provide the related Saffir-Simpson category, season, wind speed, and SST for 15 days before and after the tropical cyclone genesis. more
-
Deep Learning Weather Models for Subregional Ocean Forecasting: A Case Study on the Canary Current Upwelling System¶
Oceanographic forecasting impacts various sectors of society by supporting environmental conservation and economic activities. Based on global circulation models, traditional forecasting methods are...Oceanographic forecasting impacts various sectors of society by supporting environmental conservation and economic activities. Based on global circulation models, traditional forecasting methods are computationally expensive and slow, limiting their ability to provide rapid forecasts. Recent advances in deep learning offer faster and more accurate predictions, although these data-driven models are often trained with global data from numerical simulations, which may not reflect reality. The emergence of such models presents great potential for improving ocean prediction at a subregional domain. However, their ability to predict fine-scale ocean processes, like mesoscale structures, remains largely unknown. This work aims to adapt a graph neural network initially developed for global weather forecasting to improve subregional ocean prediction, specifically focusing on the Canary Current upwelling system. The model is trained with satellite data and compared to state-of-the-art physical ocean models to assess its performance in capturing ocean dynamics. Our results show that the deep learning model surpasses traditional methods in precision despite some challenges in upwelling areas. It demonstrated superior performance in reducing RMSE errors compared to ConvLSTM and the GLORYS reanalysis, particularly in regions with complex oceanic dynamics such as Cape Ghir, Cape Bojador, and Cape Blanc. The model achieved improvements of up to 26.5% relative to ConvLSTM and error reductions of up to 76% in 5-day forecasts compared to the GLORYS reanalysis at these critical locations, highlighting its enhanced capability to capture spatial variability and improve predictive accuracy in complex areas. These findings suggest the viability of adapting meteorological data-driven models for improving subregional medium-term ocean forecasting. more
-
NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation¶
Long-term, high-fidelity simulation of slow-changing physical systems, such as the ocean and climate, presents a fundamental challenge in scientific computing. Traditional autoregressive machine...Long-term, high-fidelity simulation of slow-changing physical systems, such as the ocean and climate, presents a fundamental challenge in scientific computing. Traditional autoregressive machine learning models often fail in these tasks as minor errors accumulate and lead to rapid forecast degradation. To address this problem, we propose NeuralOM, a general neural operator framework designed for simulating complex, slow-changing dynamics. NeuralOM's core consists of two key innovations: (1) a Progressive Residual Correction Framework that decomposes the forecasting task into a series of fine-grained refinement steps, effectively suppressing long-term error accumulation; and (2) a Physics-Guided Graph Network whose built-in adaptive messaging mechanism explicitly models multi-scale physical interactions, such as gradient-driven flows and multiplicative couplings, thereby enhancing physical consistency while maintaining computational efficiency. We validate NeuralOM on the challenging task of global Subseasonal-to-Seasonal (S2S) ocean simulation. Extensive experiments demonstrate that NeuralOM not only surpasses state-of-the-art models in forecast accuracy and long-term stability, but also excels in simulating extreme events. For instance, at a 60-day lead time, NeuralOM achieves a 13.3% lower RMSE compared to the best-performing baseline, offering a stable, efficient, and physically-aware paradigm for data-driven scientific computing. Code link: https://github.com/YuanGao-YG/NeuralOM. more
-
LanTu: Dynamics-Enhanced Deep Learning for Eddy-Resolving Ocean Forecasting¶
Mesoscale eddies dominate the spatiotemporal multiscale variability of the ocean, and their impact on the energy cascade of the global ocean cannot be ignored. Eddy-resolving ocean forecasting is...Mesoscale eddies dominate the spatiotemporal multiscale variability of the ocean, and their impact on the energy cascade of the global ocean cannot be ignored. Eddy-resolving ocean forecasting is providing more reliable protection for fisheries and navigational safety, but also presents significant scientific challenges and high computational costs for traditional numerical models. Artificial intelligence (AI)-based weather and ocean forecasting systems are becoming powerful tools that balance forecast performance with computational efficiency. However, the complex multiscale features in the ocean dynamical system make AI models still face many challenges in mesoscale eddy forecasting (especially regional modelling). Here, we develop LanTu, a regional eddy-resolving ocean forecasting system based on dynamics-enhanced deep learning. We incorporate cross-scale interactions into LanTu and construct multiscale physical constraint for optimising LanTu guided by knowledge of eddy dynamics in order to improve the forecasting skill of LanTu for mesoscale evolution. The results show that LanTu outperforms the existing advanced operational numerical ocean forecasting system (NOFS) and AI-based ocean forecasting system (AI-OFS) in temperature, salinity, sea level anomaly and current prediction, with a lead time of more than 10 days. Our study highlights that dynamics-enhanced deep learning (LanTu) can be a powerful paradigm for eddy-resolving ocean forecasting. more
-
Generalizable neural-network parameterization of mesoscale eddies in idealized and global ocean models¶
Data-driven methods have become popular to parameterize the effects of mesoscale eddies in ocean models. However, they perform poorly in generalization tasks and may require retuning if the grid...Data-driven methods have become popular to parameterize the effects of mesoscale eddies in ocean models. However, they perform poorly in generalization tasks and may require retuning if the grid resolution or ocean configuration changes. We address the generalization problem by enforcing physics constraints on a neural network parameterization of mesoscale eddy fluxes. We found that the local scaling of input and output features helps to generalize to unseen grid resolutions and depths offline in the global ocean. The scaling is based on dimensional analysis and incorporates grid spacing as a length scale. We formulate our findings as a general algorithm that can be used to enforce data-driven parameterizations with dimensional scaling. The new parameterization improves the representation of kinetic and potential energy in online simulations with idealized and global ocean models. Comparison to baseline parameterizations and impact on global ocean biases are discussed. more
-
Reconstruction of Antarctic sea ice thickness from sparse satellite laser altimetry data using a partial convolutional neural network¶
The persistent lack of spatially complete Antarctic sea ice thickness (SIT) data at sub-monthly resolution has fundamentally constrained the quantitative understanding of large-scale sea ice mass...The persistent lack of spatially complete Antarctic sea ice thickness (SIT) data at sub-monthly resolution has fundamentally constrained the quantitative understanding of large-scale sea ice mass balance processes. In this study, a pan-Antarctic SIT dataset at 5-day and 12.5 km resolution was developed based on sparse Ice, Cloud and Land Elevation Satellite (ICESat: 2003-2009) and ICESat-2 (2018-2024) along-track laser altimetry SIT retrievals using a deep learning approach. The reconstructed SIT was quantitatively validated against independent upward-looking sonar (ULS) observations and showed higher accuracy than the other four satellite-derived and reanalyzed Antarctic SIT datasets. The temporal evolution of the reconstructed SIT was further validated by ULS and ICESat-2 observations. Consistent seasonal cycles and intra-seasonal tendencies across these datasets confirm the reconstruction's reliability. Beyond advancing the mechanistic understanding of Antarctic sea ice variability and climate linkages, this reconstruction dataset's near-real-time updating capability offers operational value for monitoring and forecasting the Antarctic sea ice state. more
-
Exploring the Potential of Latent Embeddings for Sea Ice Characterization using ICESat-2 Data¶
The Ice, Cloud, and Elevation Satellite-2 (ICESat-2) provides high-resolution measurements of sea ice height. Recent studies have developed machine learning methods on ICESat-2 data, primarily...The Ice, Cloud, and Elevation Satellite-2 (ICESat-2) provides high-resolution measurements of sea ice height. Recent studies have developed machine learning methods on ICESat-2 data, primarily focusing on surface type classification. However, the heavy reliance on manually collected labels requires significant time and effort for supervised learning, as it involves cross-referencing track measurements with overlapping background optical imagery. Additionally, the coincidence of ICESat-2 tracks with background images is relatively rare due to the different overpass patterns and atmospheric conditions. To address these limitations, this study explores the potential of unsupervised autoencoder on unlabeled data to derive latent embeddings. We develop autoencoder models based on Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) to reconstruct topographic sequences from ICESat-2 and derive embeddings. We then apply Uniform Manifold Approximation and Projection (UMAP) to reduce dimensions and visualize the embeddings. Our results show that embeddings from autoencoders preserve the overall structure but generate relatively more compact clusters compared to the original ICESat-2 data, indicating the potential of embeddings to lessen the number of required labels samples. more
-
Improving Significant Wave Height Prediction Using Chronos Models¶
Accurate wave height prediction is critical for maritime safety and coastal resilience, yet conventional physics-based models and traditional machine learning methods face challenges in computational...Accurate wave height prediction is critical for maritime safety and coastal resilience, yet conventional physics-based models and traditional machine learning methods face challenges in computational efficiency and nonlinear dynamics modeling. This study introduces Chronos, the first implementation of a large language model (LLM)-powered temporal architecture (Chronos) optimized for wave forecasting. Through advanced temporal pattern recognition applied to historical wave data from three strategically chosen marine zones in the Northwest Pacific basin, our framework achieves multimodal improvements: (1) 14.3% reduction in training time with 2.5x faster inference speed compared to PatchTST baselines, achieving 0.575 mean absolute scaled error (MASE) units; (2) superior short-term forecasting (1-24h) across comprehensive metrics; (3) sustained predictive leadership in extended-range forecasts (1-120h); and (4) demonstrated zero-shot capability maintaining median performance (rank 4/12) against specialized operational models. This LLM-enhanced temporal modeling paradigm establishes a new standard in wave prediction, offering both computationally efficient solutions and a transferable framework for complex geophysical systems modeling. more