Forecasting of Sea Level Time Series using RNN and LSTM Case Study in Sunda Strait

Sea-level forecasting is essential for coastal development planning and minimizing their signi?cant consequences in coastal operations, such as naval engineering and navigation. Conventional sea level predictions, such as tidal harmonic analysis, do not consider the in?uence of non-tidal elements an...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Annas Wahyu Ramadhan, Didit Adytia, Deni Saepudin, Semeidi Husrin, Adiwijaya Adiwijaya
Formato: article
Lenguaje:ID
Publicado: Universitas Udayana 2021
Materias:
Acceso en línea:https://doaj.org/article/2a9f2e5b0bf24b69b0db9e5f2c3d3a4d
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:2a9f2e5b0bf24b69b0db9e5f2c3d3a4d
record_format dspace
spelling oai:doaj.org-article:2a9f2e5b0bf24b69b0db9e5f2c3d3a4d2021-12-01T04:18:07ZForecasting of Sea Level Time Series using RNN and LSTM Case Study in Sunda Strait2088-15412541-583210.24843/LKJITI.2021.v12.i03.p01https://doaj.org/article/2a9f2e5b0bf24b69b0db9e5f2c3d3a4d2021-10-01T00:00:00Zhttps://ojs.unud.ac.id/index.php/lontar/article/view/75488https://doaj.org/toc/2088-1541https://doaj.org/toc/2541-5832Sea-level forecasting is essential for coastal development planning and minimizing their signi?cant consequences in coastal operations, such as naval engineering and navigation. Conventional sea level predictions, such as tidal harmonic analysis, do not consider the in?uence of non-tidal elements and require long-term historical sea level data. In this paper, two deep learning approaches are applied to forecast sea level. The ?rst deep learning is Recurrent Neural Network (RNN), and the second is Long Short Term Memory (LSTM). Sea level data was obtained from IDSL (Inexpensive Device for Sea Level Measurement) at Sebesi, Sunda Strait, Indonesia. We trained the model for forecasting 3, 5, 7, 10, and 14 days using three months of hourly data in 2020 from 1st May to 1st August. We compared forecasting results with RNN and LSTM with the results of the conventional method, namely tidal harmonic analysis. The LSTM’s results showed better performance than the RNN and the tidal harmonic analysis, with a correlation coef?cient of R2 0.97 and an RMSE value of 0.036 for the 14 days prediction. Moreover, RNN and LSTM can accommodate non-tidal harmonic data such as sea level anomalies.Annas Wahyu RamadhanDidit AdytiaDeni SaepudinSemeidi HusrinAdiwijaya AdiwijayaUniversitas UdayanaarticleElectronic computers. Computer scienceQA75.5-76.95IDLontar Komputer, Vol 12, Iss 3, Pp 130-140 (2021)
institution DOAJ
collection DOAJ
language ID
topic Electronic computers. Computer science
QA75.5-76.95
spellingShingle Electronic computers. Computer science
QA75.5-76.95
Annas Wahyu Ramadhan
Didit Adytia
Deni Saepudin
Semeidi Husrin
Adiwijaya Adiwijaya
Forecasting of Sea Level Time Series using RNN and LSTM Case Study in Sunda Strait
description Sea-level forecasting is essential for coastal development planning and minimizing their signi?cant consequences in coastal operations, such as naval engineering and navigation. Conventional sea level predictions, such as tidal harmonic analysis, do not consider the in?uence of non-tidal elements and require long-term historical sea level data. In this paper, two deep learning approaches are applied to forecast sea level. The ?rst deep learning is Recurrent Neural Network (RNN), and the second is Long Short Term Memory (LSTM). Sea level data was obtained from IDSL (Inexpensive Device for Sea Level Measurement) at Sebesi, Sunda Strait, Indonesia. We trained the model for forecasting 3, 5, 7, 10, and 14 days using three months of hourly data in 2020 from 1st May to 1st August. We compared forecasting results with RNN and LSTM with the results of the conventional method, namely tidal harmonic analysis. The LSTM’s results showed better performance than the RNN and the tidal harmonic analysis, with a correlation coef?cient of R2 0.97 and an RMSE value of 0.036 for the 14 days prediction. Moreover, RNN and LSTM can accommodate non-tidal harmonic data such as sea level anomalies.
format article
author Annas Wahyu Ramadhan
Didit Adytia
Deni Saepudin
Semeidi Husrin
Adiwijaya Adiwijaya
author_facet Annas Wahyu Ramadhan
Didit Adytia
Deni Saepudin
Semeidi Husrin
Adiwijaya Adiwijaya
author_sort Annas Wahyu Ramadhan
title Forecasting of Sea Level Time Series using RNN and LSTM Case Study in Sunda Strait
title_short Forecasting of Sea Level Time Series using RNN and LSTM Case Study in Sunda Strait
title_full Forecasting of Sea Level Time Series using RNN and LSTM Case Study in Sunda Strait
title_fullStr Forecasting of Sea Level Time Series using RNN and LSTM Case Study in Sunda Strait
title_full_unstemmed Forecasting of Sea Level Time Series using RNN and LSTM Case Study in Sunda Strait
title_sort forecasting of sea level time series using rnn and lstm case study in sunda strait
publisher Universitas Udayana
publishDate 2021
url https://doaj.org/article/2a9f2e5b0bf24b69b0db9e5f2c3d3a4d
work_keys_str_mv AT annaswahyuramadhan forecastingofsealeveltimeseriesusingrnnandlstmcasestudyinsundastrait
AT diditadytia forecastingofsealeveltimeseriesusingrnnandlstmcasestudyinsundastrait
AT denisaepudin forecastingofsealeveltimeseriesusingrnnandlstmcasestudyinsundastrait
AT semeidihusrin forecastingofsealeveltimeseriesusingrnnandlstmcasestudyinsundastrait
AT adiwijayaadiwijaya forecastingofsealeveltimeseriesusingrnnandlstmcasestudyinsundastrait
_version_ 1718405893385617408