Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity

• URL: http://arxiv.org/abs/2507.06479v1
• Date: Wed, 09 Jul 2025 01:56:25 GMT
• Title: Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity
• Authors: Niloofar Asefi, Leonard Lupin-Jimenez, Tianning Wu, Ruoying He, Ashesh Chattopadhyay,
• Abstract summary: Reconstructing ocean dynamics from observational data is fundamentally limited by the sparse, irregular, and Lagrangian nature of spatial sampling.<n>We leverage a deep learning framework that combines neural operators with denoising diffusion probabilistic models (DDPMs) to reconstruct high-resolution ocean states.<n>We validate our method on benchmark systems, synthetic float observations, and real satellite data, demonstrating robust performance under severe spatial sampling limitations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reconstructing ocean dynamics from observational data is fundamentally limited by the sparse, irregular, and Lagrangian nature of spatial sampling, particularly in subsurface and remote regions. This sparsity poses significant challenges for forecasting key phenomena such as eddy shedding and rogue waves. Traditional data assimilation methods and deep learning models often struggle to recover mesoscale turbulence under such constraints. We leverage a deep learning framework that combines neural operators with denoising diffusion probabilistic models (DDPMs) to reconstruct high-resolution ocean states from extremely sparse Lagrangian observations. By conditioning the generative model on neural operator outputs, the framework accurately captures small-scale, high-wavenumber dynamics even at $99\%$ sparsity (for synthetic data) and $99.9\%$ sparsity (for real satellite observations). We validate our method on benchmark systems, synthetic float observations, and real satellite data, demonstrating robust performance under severe spatial sampling limitations as compared to other deep learning baselines.

Related papers

• ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided Diffusion [48.540756751934836]
  ReconMOST is a data-driven guided diffusion model framework for multi-layer sea temperature reconstruction.<n>Our method extends ML-based SST reconstruction to a global, multi-layer setting, handling over 92.5% missing data.
  arXiv  Detail & Related papers  (2025-06-12T06:27:22Z)
• Synthetic Geology -- Structural Geology Meets Deep Learning [3.216132991084434]
  Building on techniques of generative artificial intelligence applied to voxelated images, we demonstrate a method that extends surface geological data to a three-dimensional subsurface region by training a neural network.<n>We close this data gap in the development of subsurface deep learning by designing a synthetic data-generator process that mimics eons of geological activity.<n>A foundation model trained on such synthetic data is able to generate a 3D image of the subsurface from a previously unseen map of surface topography and geology.
  arXiv  Detail & Related papers  (2025-06-11T20:42:28Z)
• Advanced long-term earth system forecasting by learning the small-scale nature [74.19833913539053]
  We present Triton, an AI framework designed to address this fundamental challenge.<n>Inspired by increasing grids to explicitly resolve small scales in numerical models, Triton employs a hierarchical architecture processing information across multiple resolutions to mitigate spectral bias.<n>We demonstrate Triton's superior performance on challenging forecast tasks, achieving stable year-long global temperature forecasts, skillful Kuroshio eddy predictions till 120 days, and high-fidelity turbulence simulations.
  arXiv  Detail & Related papers  (2025-05-26T02:49:00Z)
• Modeling Spatial Extremes using Non-Gaussian Spatial Autoregressive Models via Convolutional Neural Networks [14.37149160708975]
  We present a spatial autoregressive modeling framework, which maps observations at a location and its neighbors to independent random variables.<n>In particular, we consider the SAR model with Generalized Extreme Value distribution innovations to combine the observation at a central grid location with its neighbors.<n>We apply this model to analyze annual maximum precipitation data from ERA-Interim-driven Weather Research and Forecasting (WRF) simulations.
  arXiv  Detail & Related papers  (2025-05-05T21:26:02Z)
• Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation [67.23953699167274]
  Self-supervised learning (SSL) has enabled the development of vision foundation models for Earth Observation (EO)<n>In EO, this challenge is amplified by the redundancy and heavy-tailed distributions common in satellite imagery.<n>We propose a dynamic dataset pruning strategy designed to improve SSL pre-training by maximizing dataset diversity and balance.
  arXiv  Detail & Related papers  (2025-04-09T15:13:26Z)
• Simulation-informed deep learning for enhanced SWOT observations of fine-scale ocean dynamics [4.575524892161048]
  Ocean processes at fine scales are crucial yet difficult to observe accurately due to limitations in satellite and in-situ measurements.<n>Current methods struggle with noisy data or require extensive supervised training, limiting their effectiveness on real-world observations.<n>We introduce SIMPGEN, an unsupervised adversarial learning framework combining real SWOT observations with simulated reference data.
  arXiv  Detail & Related papers  (2025-03-27T09:29:33Z)
• Deep Learning for Sea Surface Temperature Reconstruction under Cloud Occlusion [34.00878406145686]
  We describe several Machine Learning models to fill the cloud-occluded areas starting from MODIS Aqua nighttime L3 images.<n>To tackle this challenge, we employed a type of Convolutional Neural Network model (U-net) to reconstruct cloud-covered portions of satellite imagery.<n>Our best-performing architecture show 50% lower root mean square errors over established gap-filling methods.
  arXiv  Detail & Related papers  (2024-12-04T15:49:49Z)
• Attention-Based Reconstruction of Full-Field Tsunami Waves from Sparse Tsunameter Networks [0.0]
  We focus on the Tsunami Data Assimilation Method, which generates forecasts from tsunameter networks.<n>Our model is used to reconstruct high-resolution tsunami wavefields from extremely sparse observations.<n>We demonstrate that our approach significantly outperforms the Linear Interpolation with Huygens-Fresnel Principle in generating dense observation networks.
  arXiv  Detail & Related papers  (2024-11-20T00:42:40Z)
• SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
  Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. Traditional methods often struggle to capture the complex dynamics of meteorological systems. We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
  arXiv  Detail & Related papers  (2024-05-29T08:00:15Z)
• Continual Learning of Range-Dependent Transmission Loss for Underwater Acoustic using Conditional Convolutional Neural Net [0.0]
  This research aims to improve the accuracy of deep-learning models for predicting underwater radiated noise in far-field scenarios. We propose a novel range-conditional convolutional neural network that incorporates ocean bathymetry data into the input. Our proposed architecture effectively captures transmission loss over a range-dependent, varying bathymetry profile.
  arXiv  Detail & Related papers  (2024-04-11T19:13:38Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)
• Realistic Noise Synthesis with Diffusion Models [44.404059914652194]
  Deep denoising models require extensive real-world training data, which is challenging to acquire.<n>We propose a novel Realistic Noise Synthesis Diffusor (RNSD) method using diffusion models to address these challenges.
  arXiv  Detail & Related papers  (2023-05-23T12:56:01Z)
• Machine learning for phase-resolved reconstruction of nonlinear ocean wave surface elevations from sparse remote sensing data [37.69303106863453]
  We propose a novel approach for phase-resolved wave surface reconstruction using neural networks. Our approach utilizes synthetic yet highly realistic training data on uniform one-dimensional grids.
  arXiv  Detail & Related papers  (2023-05-18T12:30:26Z)
• An evaluation of deep learning models for predicting water depth evolution in urban floods [59.31940764426359]
  We compare different deep learning models for prediction of water depth at high spatial resolution. Deep learning models are trained to reproduce the data simulated by the CADDIES cellular-automata flood model. Our results show that the deep learning models present in general lower errors compared to the other methods.
  arXiv  Detail & Related papers  (2023-02-20T16:08:54Z)
• Modeling Oceanic Variables with Dynamic Graph Neural Networks [0.09830751917335563]
  We describe a data-driven method to predict environmental variables in the region of Santos-Sao Vicente-Bertioga Estuarine System in Brazil. Our model exploits both temporal and spatial inductive biases by joining state-of-the-art sequence models and relational models. Experiments show that better results are attained by our model, while maintaining flexibility and little domain knowledge dependency.
  arXiv  Detail & Related papers  (2022-06-25T22:43:02Z)

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.