利用卷积和自我关注网络从船载海洋雷达数据中估算波高

IF 2.2 3区 地球科学 Q2 OCEANOGRAPHY Ocean Dynamics Pub Date : 2023-12-28 DOI:10.1007/s10236-023-01591-7
Fupeng Wang, Xiaoliang Chu, Baoxue Zhang
{"title":"利用卷积和自我关注网络从船载海洋雷达数据中估算波高","authors":"Fupeng Wang, Xiaoliang Chu, Baoxue Zhang","doi":"10.1007/s10236-023-01591-7","DOIUrl":null,"url":null,"abstract":"<p>In this paper, a fusion model based on convolution and self-attention with multi-subimage input model (CNN-SA-MS) is proposed to estimate significant wave height (SWH) from shipborne X-band radar images. The model takes multiple radar subimages as input simultaneously, which not only improves the accuracy of SWH inversion by including more information, but also avoids the restriction of selecting a single subimage in the upwind direction and dependence on external devices for wind data provision. Based on the characteristics of radar images and computational efficiency considerations, this paper selects three radar subimages as the input for the model. The comparison data from buoys and ECMWF are used for training and testing. After averaging the results of 64 radar images, the root mean square error (RMSE) and correlation coefficient (CC) of the CNN-SA-MS model are 0.197 m and 0.903, respectively. The results show that the CNN-SA-MS model improves the accuracy and stability of SWH estimation compared to single-subimage CNN regression model. For the two time periods with significant discrepancies between radar data and ECMWF predictions, we introduce satellite altimeter information as a source of reference for evaluation. The resulting analysis indicates that the significant wave height estimates generated by CNN-SA-MS model are more reliable.</p>","PeriodicalId":19387,"journal":{"name":"Ocean Dynamics","volume":"33 6 1","pages":""},"PeriodicalIF":2.2000,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Significant wave height estimation from shipborne marine radar data using convolutional and self-attention network\",\"authors\":\"Fupeng Wang, Xiaoliang Chu, Baoxue Zhang\",\"doi\":\"10.1007/s10236-023-01591-7\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>In this paper, a fusion model based on convolution and self-attention with multi-subimage input model (CNN-SA-MS) is proposed to estimate significant wave height (SWH) from shipborne X-band radar images. The model takes multiple radar subimages as input simultaneously, which not only improves the accuracy of SWH inversion by including more information, but also avoids the restriction of selecting a single subimage in the upwind direction and dependence on external devices for wind data provision. Based on the characteristics of radar images and computational efficiency considerations, this paper selects three radar subimages as the input for the model. The comparison data from buoys and ECMWF are used for training and testing. After averaging the results of 64 radar images, the root mean square error (RMSE) and correlation coefficient (CC) of the CNN-SA-MS model are 0.197 m and 0.903, respectively. The results show that the CNN-SA-MS model improves the accuracy and stability of SWH estimation compared to single-subimage CNN regression model. For the two time periods with significant discrepancies between radar data and ECMWF predictions, we introduce satellite altimeter information as a source of reference for evaluation. The resulting analysis indicates that the significant wave height estimates generated by CNN-SA-MS model are more reliable.</p>\",\"PeriodicalId\":19387,\"journal\":{\"name\":\"Ocean Dynamics\",\"volume\":\"33 6 1\",\"pages\":\"\"},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2023-12-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ocean Dynamics\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1007/s10236-023-01591-7\",\"RegionNum\":3,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"OCEANOGRAPHY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ocean Dynamics","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1007/s10236-023-01591-7","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OCEANOGRAPHY","Score":null,"Total":0}
引用次数: 0

摘要

本文提出了一种基于卷积和自注意的多子图像输入模型(CNN-SA-MS)融合模型,用于从船载 X 波段雷达图像估算显著波高(SWH)。该模型将多个雷达子图像同时作为输入,不仅通过包含更多信息提高了 SWH 反演的准确性,而且避免了只选择上风方向单个子图像的限制和风数据提供对外部设备的依赖。基于雷达图像的特点和计算效率的考虑,本文选择三个雷达子图像作为模型的输入。来自浮标和 ECMWF 的对比数据用于训练和测试。对 64 幅雷达图像的结果取平均值后,CNN-SA-MS 模型的均方根误差(RMSE)和相关系数(CC)分别为 0.197 m 和 0.903。结果表明,与单子图像 CNN 回归模型相比,CNN-SA-MS 模型提高了 SWH 估计的精度和稳定性。对于雷达数据与 ECMWF 预测值差异较大的两个时段,我们引入了卫星高度计信息作为评估的参考源。结果分析表明,CNN-SA-MS 模型生成的显著波高估计值更为可靠。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Significant wave height estimation from shipborne marine radar data using convolutional and self-attention network

In this paper, a fusion model based on convolution and self-attention with multi-subimage input model (CNN-SA-MS) is proposed to estimate significant wave height (SWH) from shipborne X-band radar images. The model takes multiple radar subimages as input simultaneously, which not only improves the accuracy of SWH inversion by including more information, but also avoids the restriction of selecting a single subimage in the upwind direction and dependence on external devices for wind data provision. Based on the characteristics of radar images and computational efficiency considerations, this paper selects three radar subimages as the input for the model. The comparison data from buoys and ECMWF are used for training and testing. After averaging the results of 64 radar images, the root mean square error (RMSE) and correlation coefficient (CC) of the CNN-SA-MS model are 0.197 m and 0.903, respectively. The results show that the CNN-SA-MS model improves the accuracy and stability of SWH estimation compared to single-subimage CNN regression model. For the two time periods with significant discrepancies between radar data and ECMWF predictions, we introduce satellite altimeter information as a source of reference for evaluation. The resulting analysis indicates that the significant wave height estimates generated by CNN-SA-MS model are more reliable.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Ocean Dynamics
Ocean Dynamics 地学-海洋学
CiteScore
5.40
自引率
0.00%
发文量
37
审稿时长
6-12 weeks
期刊介绍: Ocean Dynamics is an international journal that aims to publish high-quality peer-reviewed articles in the following areas of research: Theoretical oceanography (new theoretical concepts that further system understanding with a strong view to applicability for operational or monitoring purposes); Computational oceanography (all aspects of ocean modeling and data analysis); Observational oceanography (new techniques or systematic approaches in measuring oceanic variables, including all aspects of monitoring the state of the ocean); Articles with an interdisciplinary character that encompass research in the fields of biological, chemical and physical oceanography are especially encouraged.
期刊最新文献
A new high-resolution Coastal Ice-Ocean Prediction System for the East Coast of Canada Improvement of drag coefficient parameterization of WAVEWATCH-III using remotely sensed products during tropical cyclones Surface ocean conditions of the Arabian Sea using two different wind forcings in the regional ocean modelling system setup Assessment of tidal current potential in the Amapá’s inner continental shelf (Eastern Amazonia - Brazil) Aggregation and transport of microplastics by a cold-core ring in the southern recirculation of the Kuroshio Extension: the role of mesoscale eddies on plastic debris distribution
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1