Predicting Velocity and Direction of Ocean Surface Currents using Elman Recurrent Neural Network Method
Background: Ocean surface currents need to be monitored to minimize accidents at ship crossings. One way to predict ocean currents—and estimate the danger level of the sea—is by finding out the currents’ velocity and their future direction. Objective: This study aims to predict the velocity and di...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universitas Airlangga
2022-04-01
|
Series: | Journal of Information Systems Engineering and Business Intelligence |
Online Access: | https://e-journal.unair.ac.id/JISEBI/article/view/30682 |
_version_ | 1811159664174301184 |
---|---|
author | Eka Alifia Kusnanti Dian C. Rini Novitasari Fajar Setiawan Aris Fanani Mohammad Hafiyusholeh Ghaluh Indah Permata Sari |
author_facet | Eka Alifia Kusnanti Dian C. Rini Novitasari Fajar Setiawan Aris Fanani Mohammad Hafiyusholeh Ghaluh Indah Permata Sari |
author_sort | Eka Alifia Kusnanti |
collection | DOAJ |
description | Background: Ocean surface currents need to be monitored to minimize accidents at ship crossings. One way to predict ocean currents—and estimate the danger level of the sea—is by finding out the currents’ velocity and their future direction.
Objective: This study aims to predict the velocity and direction of ocean surface currents.
Methods: This research uses the Elman recurrent neural network (ERNN). This study used 3,750 long-term data and 72 short-term data.
Results: The evaluation with Mean Absolute Percentage Error (MAPE) achieved the best results in short-term predictions. The best MAPE of the U currents (east to west) was 14.0279% with five inputs; the first and second hidden layers were 50 and 100, and the learning rate was 0.3. While the best MAPE of the V currents (north to south) was 3.1253% with five inputs, the first and second hidden layers were 20 and 50, and the learning rate was 0.1. The ocean surface currents’ prediction indicates that the current state is from east to south with a magnitude of around 169,5773°-175,7127° resulting in a MAPE of 0.0668%.
Conclusion: ERNN is more effective than single exponential smoothing and RBFNN in ocean current prediction studies because it produces a smaller error value. In addition, the ERNN method is good for short-term ocean surface currents but is not optimal for long-term current predictions.
Keywords: MAPE, ERNN, ocean currents, ocean currents’ velocity, ocean currents’ directions |
first_indexed | 2024-04-10T05:45:00Z |
format | Article |
id | doaj.art-1a1987cb94974c34886112be77f4d088 |
institution | Directory Open Access Journal |
issn | 2598-6333 2443-2555 |
language | English |
last_indexed | 2024-04-10T05:45:00Z |
publishDate | 2022-04-01 |
publisher | Universitas Airlangga |
record_format | Article |
series | Journal of Information Systems Engineering and Business Intelligence |
spelling | doaj.art-1a1987cb94974c34886112be77f4d0882023-03-06T02:56:32ZengUniversitas AirlanggaJournal of Information Systems Engineering and Business Intelligence2598-63332443-25552022-04-0181213010.20473/jisebi.8.1.21-3025105Predicting Velocity and Direction of Ocean Surface Currents using Elman Recurrent Neural Network MethodEka Alifia Kusnanti0Dian C. Rini Novitasari1https://orcid.org/0000-0003-1593-6808Fajar Setiawan2Aris Fanani3https://orcid.org/0000-0001-7016-0286Mohammad Hafiyusholeh4https://orcid.org/0000-0003-0183-574XGhaluh Indah Permata Sari5Universitas Islam Negeri Sunan Ampel Surabaya, IndonesiaUniversitas Islam Negeri Sunan Ampel Surabaya, IndonesiaBadan Meteorologi, Klimatologi, dan Geofisika Maritim Tanjung Perak Surabaya, IndonesiaUniversitas Islam Negeri Sunan Ampel Surabaya, IndonesiaUniversitas Islam Negeri Sunan Ampel Surabaya, IndonesiaNational Taiwan University of Science and Technology, TaiwanBackground: Ocean surface currents need to be monitored to minimize accidents at ship crossings. One way to predict ocean currents—and estimate the danger level of the sea—is by finding out the currents’ velocity and their future direction. Objective: This study aims to predict the velocity and direction of ocean surface currents. Methods: This research uses the Elman recurrent neural network (ERNN). This study used 3,750 long-term data and 72 short-term data. Results: The evaluation with Mean Absolute Percentage Error (MAPE) achieved the best results in short-term predictions. The best MAPE of the U currents (east to west) was 14.0279% with five inputs; the first and second hidden layers were 50 and 100, and the learning rate was 0.3. While the best MAPE of the V currents (north to south) was 3.1253% with five inputs, the first and second hidden layers were 20 and 50, and the learning rate was 0.1. The ocean surface currents’ prediction indicates that the current state is from east to south with a magnitude of around 169,5773°-175,7127° resulting in a MAPE of 0.0668%. Conclusion: ERNN is more effective than single exponential smoothing and RBFNN in ocean current prediction studies because it produces a smaller error value. In addition, the ERNN method is good for short-term ocean surface currents but is not optimal for long-term current predictions. Keywords: MAPE, ERNN, ocean currents, ocean currents’ velocity, ocean currents’ directionshttps://e-journal.unair.ac.id/JISEBI/article/view/30682 |
spellingShingle | Eka Alifia Kusnanti Dian C. Rini Novitasari Fajar Setiawan Aris Fanani Mohammad Hafiyusholeh Ghaluh Indah Permata Sari Predicting Velocity and Direction of Ocean Surface Currents using Elman Recurrent Neural Network Method Journal of Information Systems Engineering and Business Intelligence |
title | Predicting Velocity and Direction of Ocean Surface Currents using Elman Recurrent Neural Network Method |
title_full | Predicting Velocity and Direction of Ocean Surface Currents using Elman Recurrent Neural Network Method |
title_fullStr | Predicting Velocity and Direction of Ocean Surface Currents using Elman Recurrent Neural Network Method |
title_full_unstemmed | Predicting Velocity and Direction of Ocean Surface Currents using Elman Recurrent Neural Network Method |
title_short | Predicting Velocity and Direction of Ocean Surface Currents using Elman Recurrent Neural Network Method |
title_sort | predicting velocity and direction of ocean surface currents using elman recurrent neural network method |
url | https://e-journal.unair.ac.id/JISEBI/article/view/30682 |
work_keys_str_mv | AT ekaalifiakusnanti predictingvelocityanddirectionofoceansurfacecurrentsusingelmanrecurrentneuralnetworkmethod AT diancrininovitasari predictingvelocityanddirectionofoceansurfacecurrentsusingelmanrecurrentneuralnetworkmethod AT fajarsetiawan predictingvelocityanddirectionofoceansurfacecurrentsusingelmanrecurrentneuralnetworkmethod AT arisfanani predictingvelocityanddirectionofoceansurfacecurrentsusingelmanrecurrentneuralnetworkmethod AT mohammadhafiyusholeh predictingvelocityanddirectionofoceansurfacecurrentsusingelmanrecurrentneuralnetworkmethod AT ghaluhindahpermatasari predictingvelocityanddirectionofoceansurfacecurrentsusingelmanrecurrentneuralnetworkmethod |