Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM
Predicting wave height is essential to reduce significant risks for shipping or activities carried out at sea. Waves inherit a stochastic nature, mainly generated by wind and propagated through the ocean, making them challenging to forecast. In this paper, we design time series wave forecasting usin...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ikatan Ahli Informatika Indonesia
2022-10-01
|
| Series: | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| Subjects: | |
| Online Access: | http://jurnal.iaii.or.id/index.php/RESTI/article/view/4160 |
| _version_ | 1797334352651091968 |
|---|---|
| author | Cornelius Stephanus Alfredo Didit Adytia Adytia |
| author_facet | Cornelius Stephanus Alfredo Didit Adytia Adytia |
| author_sort | Cornelius Stephanus Alfredo |
| collection | DOAJ |
| description | Predicting wave height is essential to reduce significant risks for shipping or activities carried out at sea. Waves inherit a stochastic nature, mainly generated by wind and propagated through the ocean, making them challenging to forecast. In this paper, we design time series wave forecasting using a deep learning model, which is a hybrid Convolutional Neural Network (CNN)-Gated Recurrent Unit (GRU) or CNN-GRU. We use two time series of wave data sets, i.e., reanalysis data from ERA5 by ECMWF and GFS from NOAA. As a study area, we choose Pelabuhan Ratu, located in the south of West Java which is connected to the open Indian Ocean. Moreover, we also compare the results by using other deep learning models, i.e., the Long Short-Term Memory (LSTM) and GRU. We evaluated these models to forecast 7, 14, and 30 days. Models' performance is assessed using RMSE, MAPE, and Correlation Coefficient (CC). For predicting 30 days, using the ERA5 data, the CNN-GRU model produces relatively accurate results with an RMSE value of 1.8844 and CC of 0.9938, whereas for the GFS data, results in RMSE value of 1.8852 and CC of 0.9915. |
| first_indexed | 2024-03-08T08:18:40Z |
| format | Article |
| id | doaj.art-b2b8d362e8ee4e3aa518ea0bd80568e7 |
| institution | Directory Open Access Journal |
| issn | 2580-0760 |
| language | English |
| last_indexed | 2024-03-08T08:18:40Z |
| publishDate | 2022-10-01 |
| publisher | Ikatan Ahli Informatika Indonesia |
| record_format | Article |
| series | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| spelling | doaj.art-b2b8d362e8ee4e3aa518ea0bd80568e72024-02-02T06:34:38ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602022-10-016577678110.29207/resti.v6i5.41604160Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTMCornelius Stephanus Alfredo0Didit Adytia Adytia1Telkom UniversityTelkom UniversityPredicting wave height is essential to reduce significant risks for shipping or activities carried out at sea. Waves inherit a stochastic nature, mainly generated by wind and propagated through the ocean, making them challenging to forecast. In this paper, we design time series wave forecasting using a deep learning model, which is a hybrid Convolutional Neural Network (CNN)-Gated Recurrent Unit (GRU) or CNN-GRU. We use two time series of wave data sets, i.e., reanalysis data from ERA5 by ECMWF and GFS from NOAA. As a study area, we choose Pelabuhan Ratu, located in the south of West Java which is connected to the open Indian Ocean. Moreover, we also compare the results by using other deep learning models, i.e., the Long Short-Term Memory (LSTM) and GRU. We evaluated these models to forecast 7, 14, and 30 days. Models' performance is assessed using RMSE, MAPE, and Correlation Coefficient (CC). For predicting 30 days, using the ERA5 data, the CNN-GRU model produces relatively accurate results with an RMSE value of 1.8844 and CC of 0.9938, whereas for the GFS data, results in RMSE value of 1.8852 and CC of 0.9915.http://jurnal.iaii.or.id/index.php/RESTI/article/view/4160wave height, pelabuhan ratu, cnn-gru, long short-term memory, gated recurrent unit |
| spellingShingle | Cornelius Stephanus Alfredo Didit Adytia Adytia Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) wave height, pelabuhan ratu, cnn-gru, long short-term memory, gated recurrent unit |
| title | Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM |
| title_full | Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM |
| title_fullStr | Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM |
| title_full_unstemmed | Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM |
| title_short | Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM |
| title_sort | time series forecasting of significant wave height using gru cnn gru and lstm |
| topic | wave height, pelabuhan ratu, cnn-gru, long short-term memory, gated recurrent unit |
| url | http://jurnal.iaii.or.id/index.php/RESTI/article/view/4160 |
| work_keys_str_mv | AT corneliusstephanusalfredo timeseriesforecastingofsignificantwaveheightusinggrucnngruandlstm AT diditadytiaadytia timeseriesforecastingofsignificantwaveheightusinggrucnngruandlstm |