中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 海洋研究所
  3. 中国科学院海洋研究所
  4. 海洋环流与波动重点实验室
Reconstruction of Extreme Sea Levels in coastal China using Multiple Deep Learning models

文献类型：期刊论文

作者Fang, Jiayi5,6; Huang, Jionghao5,6; Bian, Wanchao5,6; Li, Sida4; Li, Shuiqing3; Bai, Zhixu1,2; Qu, Ying10; Wu, Yanjun8,9; Zhu, Ye7
刊名SCIENTIFIC DATA
出版日期2026-01-19
卷号13期号:1页码:17
DOI10.1038/s41597-026-06593-w
通讯作者Fang, Jiayi(jyfang@hznu.edu.cn)
英文摘要We present a 1970-2020 dataset of daily maximum coastal water levels reconstructed for 23 tide gauges along China's coast. The product combines storm-surge residuals predicted with an Informer-based deep learning workflow (benchmarked against LSTM, CNN-LSTM, and ConvLSTM) with astronomical tides estimated by UTide from historical observations. Predictors are drawn from ERA5 reanalysis and multi-source tide-gauge records are used for training and validation. For each station, the model with best validation skill generates residuals combined with tidal harmonics to form daily maxima. Across stations, the reconstruction attains a mean correlation coefficient of 0.81 and RMSE of 11.7 cm for daily maxima; for events above the 95th percentile, the mean correlation is 0.68 and RMSE is typically below 20 cm. The release includes metadata, data splits, and skill metrics for transparency and reuse. This dataset enables spatiotemporal analyses of extreme coastal water levels and coastal hazard mitigation in regions with sparse observations. Daily maxima are computed as the sum of the maximum tide and maximum surge. This serves as an upper bound, as the peaks of tide and surge rarely coincide. Using hourly data, we estimate a mean non-coincidence bias of 14.9 cm (14.8%). Additionally, station-specific statistics are provided for user adjustment.
资助项目the National Natural Science Foundation of China (Grant No. 42571085) ; the National Key R&D Program of China (Grant No. 2023YFC3008100)
WOS研究方向Science & Technology - Other Topics
语种英语
WOS记录号WOS:001694648200002
出版者NATURE PORTFOLIO
源URL[http://ir.qdio.ac.cn/handle/337002/204811]  
专题海洋研究所_海洋环流与波动重点实验室
通讯作者Fang, Jiayi
作者单位1.Zhejiang Collaborat Innovat Ctr Tideland Reclamat, Wenzhou 325035, Peoples R China
2.Wenzhou Univ, Coll Civil Engn & Architecture, Wenzhou 325035, Peoples R China
3.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Observat & Forecasting, Key Lab Ocean Circulat & Waves, Qingdao 266071, Peoples R China
4.Jiangsu Ocean Univ, Lianyungang 222000, Peoples R China
5.Hangzhou Normal Univ, Inst Remote Sensing & Earth Sci, Hangzhou 311121, Peoples R China
6.Zhejiang Prov Key Lab Wetland Intelligent Monitori, Hangzhou 311121, Peoples R China
7.Zhejiang Marine Monitoring & Forecasting Ctr, Hangzhou 310007, Peoples R China
8.Ningbo Univ, Ningbo Univ Collaborat Innovat Ctr Land & Marine S, Ningbo 315211, Peoples R China
9.Ningbo Univ, Zhejiang Collaborat Innovat Ctr, Dept Geog & Spatial Informat Tech, Ningbo 315211, Peoples R China
10.Suzhou Univ Sci & Technol, Sch Geog Sci & Geomat Engn, Suzhou 215009, Peoples R China
推荐引用方式
GB/T 7714		 Fang, Jiayi,Huang, Jionghao,Bian, Wanchao,et al. Reconstruction of Extreme Sea Levels in coastal China using Multiple Deep Learning models[J]. SCIENTIFIC DATA,2026,13(1):17.
APA Fang, Jiayi.,Huang, Jionghao.,Bian, Wanchao.,Li, Sida.,Li, Shuiqing.,...&Zhu, Ye.(2026).Reconstruction of Extreme Sea Levels in coastal China using Multiple Deep Learning models.SCIENTIFIC DATA,13(1),17.
MLA Fang, Jiayi,et al."Reconstruction of Extreme Sea Levels in coastal China using Multiple Deep Learning models".SCIENTIFIC DATA 13.1(2026):17.

入库方式： OAI收割

来源：海洋研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。