Simulation-informed deep learning for enhanced SWOT observations of fine-scale ocean dynamics

2025-03-27

AI Summary

SWOT sea surface height (SSH) data suffer from severe contamination by systematic noise—particularly striping and phase errors—that obscures fine-scale oceanic features (e.g., mesoscale eddies, fronts). Existing denoising methods either rely on ground-truth SSH labels or lack sufficient physical fidelity. Method: We propose SIMPGEN, an unsupervised adversarial learning framework featuring a novel waveguide wavelet neural metric—a differentiable, physics-informed similarity measure integrating wave propagation priors—to guide a generative ensemble network for robust noise-signal separation. Without requiring true SSH labels, SIMPGEN jointly leverages high-fidelity numerical simulations and real SWOT observations, embedding dynamical constraints to ensure physical consistency of reconstructions. Contribution/Results: On real SWOT data, SIMPGEN achieves superior suppression of striping and phase noise, significantly outperforming state-of-the-art neural denoisers in fine-scale structural fidelity. The physically grounded outputs serve as high-credibility inputs for data assimilation and super-resolution SSH inversion.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Semi-Supervised Learning
• Natural Language Processing: Generation

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Oceanic processes at fine scales are crucial yet difficult to observe accurately due to limitations in satellite and in-situ measurements. The Surface Water and Ocean Topography (SWOT) mission provides high-resolution Sea Surface Height (SSH) data, though noise patterns often obscure fine scale structures. Current methods struggle with noisy data or require extensive supervised training, limiting their effectiveness on real-world observations. We introduce SIMPGEN (Simulation-Informed Metric and Prior for Generative Ensemble Networks), an unsupervised adversarial learning framework combining real SWOT observations with simulated reference data. SIMPGEN leverages wavelet-informed neural metrics to distinguish noisy from clean fields, guiding realistic SSH reconstructions. Applied to SWOT data, SIMPGEN effectively removes noise, preserving fine-scale features better than existing neural methods. This robust, unsupervised approach not only improves SWOT SSH data interpretation but also demonstrates strong potential for broader oceanographic applications, including data assimilation and super-resolution.

Problem

• Enhancing SWOT observations of fine-scale ocean dynamics
• Removing noise from SWOT Sea Surface Height data
• Improving unsupervised reconstruction of fine-scale ocean features

Innovation

• Unsupervised adversarial learning with simulated data
• Wavelet-informed neural metrics for noise distinction
• Robust SSH reconstruction preserving fine-scale features