Prediction of Sea Surface Current Velocity and Direction Using LSTM
| Main Authors: | Zulfa, Irkhana Indaka, Novitasari, Dian Candra Rini, Setiawan, Fajar, Fanani, Aris, Hafiyusholeh, Moh. |
|---|---|
| Format: | Article info application/pdf Journal |
| Bahasa: | eng |
| Terbitan: |
IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia
, 2021
|
| Subjects: | |
| Online Access: |
https://journal.ugm.ac.id/ijeis/article/view/63669 https://journal.ugm.ac.id/ijeis/article/view/63669/31169 |
| ctrlnum |
article-63669 |
|---|---|
| fullrecord |
<?xml version="1.0"?>
<dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd"><title lang="en-US">Prediction of Sea Surface Current Velocity and Direction Using LSTM</title><creator>Zulfa, Irkhana Indaka</creator><creator>Novitasari, Dian Candra Rini</creator><creator>Setiawan, Fajar</creator><creator>Fanani, Aris</creator><creator>Hafiyusholeh, Moh.</creator><subject lang="en-US">Depp Learning; Long Short-Term Memory</subject><subject lang="en-US">LSTM; Labuan Bajo; Sea Surface Current Velocity; Predict</subject><description lang="en-US"> Labuan Bajo is considered to have an important role as a transportation route for traders and tourists. Therefore, it is necessary to have a further understanding of the condition of the waters in Labuan Bajo, one of them is sea currents. The purpose of this research is to predict sea surface flow velocity and direction using LSTM. There are many prediction methods, one of them is Long short-term memory (LSTM). The fundamental of LSTM is to process information from the previous memory by going through three gates, that is forget gate, input gate, and output gate so the output will be the input in the next process. Based on trials with several parameters namely Hidden Layer, Learning Rate, Batch Size, and Learning rate drop period, it achieved the smallest MAPE values of U and V components of 14.15% and 8.43% with 50 hidden layers, 32 Batch size and 150 Learn rate drop.  </description><publisher lang="en-US">IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.</publisher><contributor lang="en-US"/><date>2021-04-30</date><type>Journal:Article</type><type>Other:info:eu-repo/semantics/publishedVersion</type><type>Other:</type><type>File:application/pdf</type><identifier>https://journal.ugm.ac.id/ijeis/article/view/63669</identifier><identifier>10.22146/ijeis.63669</identifier><source lang="en-US">IJEIS (Indonesian Journal of Electronics and Instrumentation Systems); Vol 11, No 1 (2021): April; 93-102</source><source>2460-7681</source><source>2088-3714</source><language>eng</language><relation>https://journal.ugm.ac.id/ijeis/article/view/63669/31169</relation><rights lang="en-US">Copyright (c) 2021 IJEIS (Indonesian Journal of Electronics and Instrumentation Systems)</rights><rights lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</rights><recordID>article-63669</recordID></dc>
|
| language |
eng |
| format |
Journal:Article Journal Other:info:eu-repo/semantics/publishedVersion Other Other: File:application/pdf File Journal:Journal |
| author |
Zulfa, Irkhana Indaka Novitasari, Dian Candra Rini Setiawan, Fajar Fanani, Aris Hafiyusholeh, Moh. |
| title |
Prediction of Sea Surface Current Velocity and Direction Using LSTM |
| publisher |
IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia |
| publishDate |
2021 |
| topic |
Depp Learning Long Short-Term Memory LSTM Labuan Bajo Sea Surface Current Velocity Predict |
| url |
https://journal.ugm.ac.id/ijeis/article/view/63669 https://journal.ugm.ac.id/ijeis/article/view/63669/31169 |
| contents |
Labuan Bajo is considered to have an important role as a transportation route for traders and tourists. Therefore, it is necessary to have a further understanding of the condition of the waters in Labuan Bajo, one of them is sea currents. The purpose of this research is to predict sea surface flow velocity and direction using LSTM. There are many prediction methods, one of them is Long short-term memory (LSTM). The fundamental of LSTM is to process information from the previous memory by going through three gates, that is forget gate, input gate, and output gate so the output will be the input in the next process. Based on trials with several parameters namely Hidden Layer, Learning Rate, Batch Size, and Learning rate drop period, it achieved the smallest MAPE values of U and V components of 14.15% and 8.43% with 50 hidden layers, 32 Batch size and 150 Learn rate drop. |
| id |
IOS1089.article-63669 |
| institution |
Universitas Gadjah Mada |
| institution_id |
19 |
| institution_type |
library:university library |
| library |
Perpustakaan Pusat Universitas Gadjah Mada |
| library_id |
488 |
| collection |
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) |
| repository_id |
1089 |
| subject_area |
Rekayasa |
| city |
SLEMAN |
| province |
DAERAH ISTIMEWA YOGYAKARTA |
| repoId |
IOS1089 |
| first_indexed |
2022-01-01T16:44:23Z |
| last_indexed |
2022-01-01T16:44:23Z |
| recordtype |
dc |
| _version_ |
1766849362540888064 |
| score |
16.845257 |