Prediction of Sea Surface Current Velocity and Direction using Gated Recurrent Unit (GRU)

Elen Riswana Safila Putri, D. C. R. Novitasari, F. Setiawan, Abdulloh Hamid, Dwi Susanto, Muhammad Fahmi
{"title":"Prediction of Sea Surface Current Velocity and Direction using Gated Recurrent Unit (GRU)","authors":"Elen Riswana Safila Putri, D. C. R. Novitasari, F. Setiawan, Abdulloh Hamid, Dwi Susanto, Muhammad Fahmi","doi":"10.1109/IAICT55358.2022.9887516","DOIUrl":null,"url":null,"abstract":"The development of tourism activities in Labuan Bajo, especially in marine tourism, which is increasing, shows the need for knowledge regarding the conditions of the water area. One of the components in these waters is the condition of the ocean currents in Labuan Bajo. Therefore, this study aims to predict the sea surface's current velocity and direction. This study uses the Gated Recurrent Unit (GRU) algorithm. The data used in this study is the u component, namely the current velocity from east to west, and the component v is the current velocity from north to south. The data is processed through two gates, namely the update gate and the reset gate. The results of the output are used as input in the next stage. Based on trials with several parameters, 50 hidden layers, 32 batch size, and 150 learning rate drop with 70:30 data division, the smallest MAPE value for u component is 9.32% and the v component is 27.94%. he calculation of the sea surface currents direction at u and v component points is towards the southwest with a range between 207° and 213°.","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IAICT55358.2022.9887516","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

The development of tourism activities in Labuan Bajo, especially in marine tourism, which is increasing, shows the need for knowledge regarding the conditions of the water area. One of the components in these waters is the condition of the ocean currents in Labuan Bajo. Therefore, this study aims to predict the sea surface's current velocity and direction. This study uses the Gated Recurrent Unit (GRU) algorithm. The data used in this study is the u component, namely the current velocity from east to west, and the component v is the current velocity from north to south. The data is processed through two gates, namely the update gate and the reset gate. The results of the output are used as input in the next stage. Based on trials with several parameters, 50 hidden layers, 32 batch size, and 150 learning rate drop with 70:30 data division, the smallest MAPE value for u component is 9.32% and the v component is 27.94%. he calculation of the sea surface currents direction at u and v component points is towards the southwest with a range between 207° and 213°.
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
基于门控循环单元(GRU)的海面流速度和方向预测
纳闽巴霍岛旅游活动的发展,特别是正在增加的海洋旅游,表明需要了解该水域的情况。这些水域的组成部分之一是纳闽巴霍的洋流状况。因此,本研究旨在预测海面洋流的速度和方向。本研究采用门控循环单元(GRU)算法。本研究使用的数据为u分量,即自东向西的流速,v分量为自北向南的流速。数据通过两个门处理,即更新门和复位门。输出的结果用作下一阶段的输入。基于多个参数、50个隐藏层、32个批大小、150个学习率下降、70:30数据分割的试验,u分量的最小MAPE值为9.32%,v分量的最小MAPE值为27.94%。计算得到u和v分量点的海流方向为西南方向,范围在207°~ 213°之间。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
A Survey of Machine Learning Approaches for Detecting Depression Using Smartphone Data Design of a Personal Digital Assistant for the Visually Challenged AutoSW: a new automated sliding window-based change point detection method for sensor data DOTA 2 Win Loss Prediction from Item and Hero Data with Machine Learning Hardware Realization of Sigmoid and Hyperbolic Tangent Activation Functions
×
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