Tao Lv , Aifeng Tao , Yuzhu Pearl Li , Gang Wang , Yuanzhang Zhu , Jinhai Zheng
{"title":"稀疏观测条件下观测点选择与波场重构的新框架","authors":"Tao Lv , Aifeng Tao , Yuzhu Pearl Li , Gang Wang , Yuanzhang Zhu , Jinhai Zheng","doi":"10.1016/j.coastaleng.2025.104836","DOIUrl":null,"url":null,"abstract":"<div><div>In the context of increasingly frequent typhoons, tropical cyclones, and severe coastal storms that pose growing risks to maritime safety and offshore infrastructure, accurate reconstruction of ocean wave fields under sparse observation conditions has become a critical yet underexplored challenge. We propose a hybrid neural network model that integrates physical prior knowledge into a deep learning framework to optimize key observation point selection and enable high-accuracy reconstruction of wave statistics. The model comprises a U-Net-based decision network (Actor) for selecting observation points and a U-Net–GAN-based reconstruction network (Critic) for wave field recovery. A hybrid loss function incorporating physical constraints and region-specific sensitivity heatmaps guides the model toward high-impact observation areas, while spatial clustering strategies ensure broad spatial coverage. The closed-loop optimization mechanism leverages reconstruction error feedback to iteratively refine both observation strategies and reconstruction performance. Experiments using hourly multi-variable ERA5 reanalysis data in the South China Sea demonstrate that, under sparse observation settings, our approach significantly outperforms conventional deployment strategies in reconstruction accuracy, validating its effectiveness for resource-constrained marine monitoring applications.</div></div>","PeriodicalId":50996,"journal":{"name":"Coastal Engineering","volume":"202 ","pages":"Article 104836"},"PeriodicalIF":4.5000,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A new framework for selecting observation points and reconstructing wave fields under sparse observations\",\"authors\":\"Tao Lv , Aifeng Tao , Yuzhu Pearl Li , Gang Wang , Yuanzhang Zhu , Jinhai Zheng\",\"doi\":\"10.1016/j.coastaleng.2025.104836\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>In the context of increasingly frequent typhoons, tropical cyclones, and severe coastal storms that pose growing risks to maritime safety and offshore infrastructure, accurate reconstruction of ocean wave fields under sparse observation conditions has become a critical yet underexplored challenge. We propose a hybrid neural network model that integrates physical prior knowledge into a deep learning framework to optimize key observation point selection and enable high-accuracy reconstruction of wave statistics. The model comprises a U-Net-based decision network (Actor) for selecting observation points and a U-Net–GAN-based reconstruction network (Critic) for wave field recovery. A hybrid loss function incorporating physical constraints and region-specific sensitivity heatmaps guides the model toward high-impact observation areas, while spatial clustering strategies ensure broad spatial coverage. The closed-loop optimization mechanism leverages reconstruction error feedback to iteratively refine both observation strategies and reconstruction performance. Experiments using hourly multi-variable ERA5 reanalysis data in the South China Sea demonstrate that, under sparse observation settings, our approach significantly outperforms conventional deployment strategies in reconstruction accuracy, validating its effectiveness for resource-constrained marine monitoring applications.</div></div>\",\"PeriodicalId\":50996,\"journal\":{\"name\":\"Coastal Engineering\",\"volume\":\"202 \",\"pages\":\"Article 104836\"},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2025-07-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Coastal Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0378383925001413\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Coastal Engineering","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0378383925001413","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0
摘要
在日益频繁的台风、热带气旋和严重的沿海风暴对海上安全和海上基础设施构成越来越大的风险的背景下,在稀疏观测条件下准确重建海浪场已成为一个关键但尚未得到充分探索的挑战。我们提出了一种混合神经网络模型,该模型将物理先验知识集成到深度学习框架中,以优化关键观测点的选择并实现波浪统计的高精度重建。该模型包括基于u - net的观测点选择决策网络(Actor)和基于u - net - gan的波场恢复重建网络(Critic)。结合物理约束和区域特定敏感性热图的混合损失函数将模型引导到高影响观测区域,而空间聚类策略确保了广泛的空间覆盖。闭环优化机制利用重建误差反馈迭代优化观测策略和重建性能。利用南海每小时多变量ERA5再分析数据进行的实验表明,在稀疏观测设置下,我们的方法在重建精度上显著优于传统部署策略,验证了其在资源有限的海洋监测应用中的有效性。
A new framework for selecting observation points and reconstructing wave fields under sparse observations
In the context of increasingly frequent typhoons, tropical cyclones, and severe coastal storms that pose growing risks to maritime safety and offshore infrastructure, accurate reconstruction of ocean wave fields under sparse observation conditions has become a critical yet underexplored challenge. We propose a hybrid neural network model that integrates physical prior knowledge into a deep learning framework to optimize key observation point selection and enable high-accuracy reconstruction of wave statistics. The model comprises a U-Net-based decision network (Actor) for selecting observation points and a U-Net–GAN-based reconstruction network (Critic) for wave field recovery. A hybrid loss function incorporating physical constraints and region-specific sensitivity heatmaps guides the model toward high-impact observation areas, while spatial clustering strategies ensure broad spatial coverage. The closed-loop optimization mechanism leverages reconstruction error feedback to iteratively refine both observation strategies and reconstruction performance. Experiments using hourly multi-variable ERA5 reanalysis data in the South China Sea demonstrate that, under sparse observation settings, our approach significantly outperforms conventional deployment strategies in reconstruction accuracy, validating its effectiveness for resource-constrained marine monitoring applications.
期刊介绍:
Coastal Engineering is an international medium for coastal engineers and scientists. Combining practical applications with modern technological and scientific approaches, such as mathematical and numerical modelling, laboratory and field observations and experiments, it publishes fundamental studies as well as case studies on the following aspects of coastal, harbour and offshore engineering: waves, currents and sediment transport; coastal, estuarine and offshore morphology; technical and functional design of coastal and harbour structures; morphological and environmental impact of coastal, harbour and offshore structures.