SSTODE: Ocean-Atmosphere Physics-Informed Neural ODEs for Sea Surface Temperature Prediction

• URL: http://arxiv.org/abs/2511.05629v1
• Date: Fri, 07 Nov 2025 03:43:53 GMT
• Title: SSTODE: Ocean-Atmosphere Physics-Informed Neural ODEs for Sea Surface Temperature Prediction
• Authors: Zheng Jiang, Wei Wang, Gaowei Zhang, Yi Wang,
• Abstract summary: Sea Surface Temperature (SST) is crucial for understanding upper-ocean thermal dynamics and ocean-atmosphere interactions.<n>SSTODE is a physics-informed Neural Ordinary Differential Equations (Neural ODEs) framework for SST prediction.<n>SSTODE achieves state-of-the-art performances in global and regional SST forecasting benchmarks.
• Score: 14.53497115906873
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Hierarchical Testing of a Hybrid Machine Learning-Physics Global Atmosphere Model [9.985969370583426]
  Machine learning (ML)-based models have demonstrated high skill and computational efficiency, often outperforming conventional physics-based models in weather and subseasonal predictions.<n>Here, we design three sets of experiments targeting synoptic-scale phenomena, interannual variability, and out-of-distribution uniform-warming forcings.<n>We evaluate the Neural General Circulation Model (NeuralGCM), a hybrid model integrating a dynamical core with ML-based component, against observations and physics-based Earth system models (ESMs).
  arXiv  Detail & Related papers  (2026-02-11T19:34:50Z)
• Leveraging an Atmospheric Foundational Model for Subregional Sea Surface Temperature Forecasting [0.0]
  We adapt a deep learning model to predict sea temperature (SST) in the Canary Upwelling System.<n>By fine-tuning this model with high-resolution oceanographic reanalysis data, we demonstrate its ability to capture complex patterns.<n>The model successfully reproduces large-scale SST structures but faces challenges in capturing finer details in coastal regions.
  arXiv  Detail & Related papers  (2025-10-29T14:30:12Z)
• VISION: Prompting Ocean Vertical Velocity Reconstruction from Incomplete Observations [43.810496295396355]
  We build and release KD48, a high-resolution ocean dynamics benchmark from petascale simulations.<n>We then introduce VISION, a novel reconstruction paradigm based on Dynamic Prompting.<n>The essence of VISION lies in its ability to generate a visual prompt on-the-fly from any available subset of observations.
  arXiv  Detail & Related papers  (2025-09-25T19:41:20Z)
• OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction [70.48962924608033]
  This work presents the first systematic effort to construct an Ocean Knowledge Graph (OKG) specifically designed to represent diverse ocean knowledge for SST prediction.<n>We develop a graph embedding network to learn the comprehensive semantic and structural knowledge within the OKG, capturing both the unique characteristics of individual sea regions and the complex correlations between them. Finally, we align the learned knowledge with fine-grained numerical SST data and leverage a pre-trained LLM to model SST patterns for accurate prediction.
  arXiv  Detail & Related papers  (2025-07-31T02:06:03Z)
• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Model [0.6008008212472723]
  We present the Ocean-linked-atmosphere (Ola) model, a high-resolution (0.25deg) Artificial Intelligence/ Machine Learning (AI/ML) coupled earth-system model. We find that Ola exhibits learned characteristics of ocean-atmosphere coupled dynamics including tropical oceanic waves with appropriate phase speeds. We present initial evidence of skill in forecasting the El Nino/Southern Oscillation (ENSO) which compares favorably to the SPEAR model of the Geophysical Fluid Dynamics Laboratory.
  arXiv  Detail & Related papers  (2024-06-12T20:29:14Z)
• Data-driven Global Ocean Modeling for Seasonal to Decadal Prediction [39.7461632644892]
  ORCA-DL is the first data-driven 3D ocean model for seasonal to decadal prediction of global ocean circulation. It accurately simulates three-dimensional ocean dynamics and outperforms state-of-the-art dynamical models. It stably emulates ocean dynamics at decadal timescales, demonstrating its potential even for skillful decadal predictions and climate projections.
  arXiv  Detail & Related papers  (2024-05-24T10:23:17Z)
• DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction [45.778221193374755]
  This paper introduces a new Lagrangian-Eulerian combined paradigm to tackle the tanglesome fluid dynamics. Instead of solely predicting the future based on Eulerian observations, we propose DeepLag to discover hidden Lagrangian dynamics within the fluid. DeepLag excels in three challenging fluid prediction tasks covering 2D and 3D, simulated and real-world fluids.
  arXiv  Detail & Related papers  (2024-02-04T09:45:35Z)
• Physics-driven machine learning for the prediction of coronal mass ejections' travel times [46.58747894238344]
  Coronal Mass Ejections (CMEs) correspond to dramatic expulsions of plasma and magnetic field from the solar corona into the heliosphere. CMEs are correlated to geomagnetic storms and may induce the generation of Solar Energetic Particles streams. The present paper introduces a physics-driven artificial intelligence approach to the prediction of CMEs travel time.
  arXiv  Detail & Related papers  (2023-05-17T08:53:29Z)
• Physical Knowledge Enhanced Deep Neural Network for Sea Surface Temperature Prediction [29.989387641655625]
  We introduce a method for Sea Surface Temperature (SST) prediction that transfers physical knowledge from historical observations to numerical models. Specifically, we use a combination of an encoder and a generative adversarial network (GAN) to capture physical knowledge from the observed data. The numerical model data is then fed into the pre-trained model to generate physics-enhanced data, which can then be used for SST prediction.
  arXiv  Detail & Related papers  (2023-04-19T02:08:54Z)
• Towards Spatio-temporal Sea Surface Temperature Forecasting via Static and Dynamic Learnable Personalized Graph Convolution Network [9.189893653029076]
  This paper proposes a novel static and dynamic learnable personalized graph convolution network (SD-LPGC) Specifically, two graph learning layers are first constructed to respectively model the stable long-term and short-term evolutionary patterns hidden in the SST signals. Then, a learnable personalized convolution layer is designed to fuse this information.
  arXiv  Detail & Related papers  (2023-04-12T14:35:38Z)
• Physics-Guided Generative Adversarial Networks for Sea Subsurface Temperature Prediction [24.55780949103687]
  Sea subsurface temperature is affected by global warming in climate change. Existing research is commonly based on either physics-based numerical models or data based models. We propose a novel framework based on generative adversarial network (GAN) combined with numerical model to predict sea subsurface temperature.
  arXiv  Detail & Related papers  (2021-11-04T23:46:51Z)
• Variational Data Assimilation with a Learned Inverse Observation Operator [46.92601529878414]
  We show how observational data can be used to improve optimizability in a system. We employ this to better behave across a chaotic system.
  arXiv  Detail & Related papers  (2021-02-22T17:16:01Z)
• Analog cosmological reheating in an ultracold Bose gas [58.720142291102135]
  We quantum-simulate the reheating-like dynamics of a generic cosmological single-field model in an ultracold Bose gas. Expanding spacetime as well as the background oscillating inflaton field are mimicked in the non-relativistic limit. The proposed experiment has the potential of exploring the evolution up to late times even beyond the weak coupling regime.
  arXiv  Detail & Related papers  (2020-08-05T18:00:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.