Physics-Guided Spatiotemporal Learning for Coastal Wave Peak Period Estimation from Video

2026-06-11

AI Summary

This study addresses the limitations of conventional nearshore wave monitoring—high cost and limited spatial coverage—and the lack of physical interpretability in existing video-based deep learning approaches. The authors propose a physics-informed spatiotemporal deep learning framework that directly estimates the dominant wave period from video data by integrating automated temporal-variance-based region-of-interest detection, a hybrid Transformer–recurrent convolutional network, simulation-to-real transfer learning, and physics-informed regularization. The method balances predictive accuracy with fluid dynamic consistency: the Transformer architecture achieves optimal instantaneous precision, while the lightweight recurrent convolutional model demonstrates superior temporal stability and operational suitability. Physics-based regularization effectively suppresses non-physical solutions, and attention mechanisms selectively focus on hydrodynamically active surf-zone regions.

Abstract

Wave parameters in the nearshore are crucial for coastal engineering, shoreline protection, marine hazard assessment, and coastal management for climate resilience. Traditional monitoring systems like buoys and radar platforms offer accurate monitoring but can have high installation and maintenance expenses and limited spatial coverage. Passive ocean monitoring using video has been achieved by leveraging deep learning, however, many methods are not physically interpretable, feasible, and validated for oceanography. In thiswork, a Physics-Guided Deep Spatiotemporal Learning Framework for direct estimation of nearshore wave peak periods from passive coastal video stream is proposed. The framework combines automated temporal-variance based region-of-interest detection, multi-stage Sim-to-Real transfer learning, and physics-informed regularization to enhance the predictive accuracy and physical consistency. A variety of spatiotemporal architectures were assessed, such as transformer-based and recurrent-convolutional ones, alongside synthetic pretraining,silver-label adaptation, and expert fine-tuning. The results show that transformer-based architectures outperformed in terms of the accuracy of the instantaneous prediction, while lightweight recurrent-convolutional architectures achieved higher temporal stability and operational oceanographic skill. Ablation studies also demonstrated the benefits of physics-guided regularization in terms of trend-following consistency, and physically implausible predictions. Explainability auditing also helped to focus attention in hydrodynamically active surf-zone regions and showed good agreement with the physically derived wave propagation behavior. In general, the proposed framework shows the promise of physics-guided video-based deep learning systems for long-term coastal wave monitoring that are cost-efficient and operationally feasible.

Problem

• coastal wave monitoring
• peak period estimation
• video-based sensing
• physics-informed learning
• spatiotemporal modeling

Innovation

• Physics-Guided Learning
• Spatiotemporal Deep Learning
• Wave Peak Period Estimation
• Sim-to-Real Transfer Learning
• Physics-Informed Regularization