A Deep Learning–Based Approach for Empirical Modeling of Single-Point Wave Spectra in Open Oceans

风浪 风浪模型 谱线 地质学 领域(数学) 电磁频谱 气象学 遥感 波浪模型 计算机科学 物理 光学 数学 天文 海洋学 纯数学
作者
Yuhao Song,Haoyu Jiang
出处
期刊:Journal of Physical Oceanography [American Meteorological Society]
卷期号:53 (9): 2089-2103 被引量:3
标识
DOI:10.1175/jpo-d-22-0198.1
摘要

Abstract Directional wave spectra are of importance for numerous practical applications such as seafaring and ocean engineering. The wave spectral densities at a certain point in the open ocean are significantly correlated to the local wind field and historical remote wind field. This feature can be used to predict the wave spectrum at that point using the wind field. In this study, a convolutional neural network (CNN) model was established to estimate wave spectra at a target point using the wind field from the ERA5 dataset. A geospatial range where the wind could impact the target point was selected, and then the historical wind field data within the range were analyzed to extract the nonlinear quantitative relationships between wind fields and wave spectra. For the spectral densities at a given direction, the wind data along the direction where waves come from were used as the input of the CNN. The model was trained to minimize the mean square error between the CNN-predicted and ERA5 reanalysis spectral density. The data structure of the wind input is reorganized into a polar grid centered on the target point to make the model applicable to different open-ocean locations worldwide. The results show that the model can predict well the wave spectrum shapes and integral wave parameters. The model allows for the prediction of single-point wave spectra in the open ocean with low computational cost and can be helpful for the study of spectral wave climate. Significance Statement The directional wave spectra (DWS) describe the distribution of wave energy among different frequencies and directions. They are useful for many marine practical applications. Usually, DWS are modeled using numerical wave models (NWMs) based on wave action balance differential equations. Although contemporary NWMs perform well after years of development, their computational costs are relatively high. The fast-developed artificial intelligence (AI) might provide an alternative solution to this task. In this study, convolutional neural networks are used to model the DWS at some selected points in the open ocean. By “learning” from NWM data, AI can effectively simulate single-point DWS in open oceans with low computational cost, which can serve as a faster data-driven surrogate model in related applications.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
1秒前
科研通AI5应助jingxian采纳,获得10
1秒前
lukawa发布了新的文献求助10
1秒前
yarazhang发布了新的文献求助10
2秒前
zhangkexin发布了新的文献求助10
2秒前
3秒前
3秒前
重要无招发布了新的文献求助10
5秒前
8秒前
8秒前
辛夷发布了新的文献求助10
9秒前
充电宝应助来来采纳,获得10
9秒前
重要无招完成签到,获得积分10
9秒前
Hanson完成签到,获得积分10
10秒前
11秒前
zhangkexin完成签到,获得积分10
11秒前
cndxh完成签到 ,获得积分10
12秒前
12秒前
12秒前
Akim应助哭泣的金鱼采纳,获得10
12秒前
合适橘完成签到,获得积分10
13秒前
聪明山芙完成签到,获得积分10
13秒前
慵懒芙芙完成签到 ,获得积分10
13秒前
jinmuna发布了新的文献求助20
13秒前
基金中中中完成签到,获得积分10
14秒前
14秒前
沈万熙发布了新的文献求助10
15秒前
乐乐发布了新的文献求助10
17秒前
18秒前
绵羊座鸭梨完成签到 ,获得积分10
19秒前
jingxian发布了新的文献求助10
22秒前
23秒前
深情安青应助斯文念波采纳,获得10
24秒前
充电宝应助清仔采纳,获得10
26秒前
bkagyin应助乐乐采纳,获得10
26秒前
lili完成签到 ,获得积分10
26秒前
27秒前
一一yi完成签到,获得积分10
28秒前
金鱼完成签到,获得积分10
29秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989589
求助须知:如何正确求助?哪些是违规求助? 3531795
关于积分的说明 11254881
捐赠科研通 3270329
什么是DOI,文献DOI怎么找? 1804966
邀请新用户注册赠送积分活动 882136
科研通“疑难数据库(出版商)”最低求助积分说明 809176