Significant wave height forecasting using long short-term memory neural network in Indonesian waters

Abdullah, F. A. R.; Ningsih, Nining Sari; Al-Khan, Titan Muslim

doi:10.1007/s40722-022-00224-3

Cited by 11 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Being excellent in describing the long-term dependence of time series, the LSTM network has also been recently applied to wave height time series prediction (Fan et al, 2020;Guan, 2020;Raja et al, 2021). Abdullah (Abdullah et al, 2022) proposed a novel modeling approach based on LSTM neural network model. It is used to predict SWH in Indonesian waters.…”

Section: Related Workmentioning

confidence: 99%

Prediction of significant wave height based on EEMD and deep learning

Song

Wang

Huo³

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

Accurate and reliable wave significant wave height(SWH) prediction is an important task for marine and engineering applications. This study aims to develop a new deep learning algorithm to accurately predict the SWH of deep and distant ocean. In this study, we combine two methods, Ensemble Empirical Mode Decomposition (EEMD) and Long Short-Term Memory (LSTM), to construct an EEMD-LSTM model, and explore the optimal parameters of the model through experiments. A total of 5328 hours of SWH data from November 30, 2020, to July 9, 2021, are used to train and test the model to predict the SWH for the future 1h, 3h, 6h, 12h, and 18h. The results show that the EEMD-LSTM model has the best results compared with other comparative models for short-term and medium- and long-term predictions. The RMSEs are 0.0204, 0.0279, 0.0452, 0.0941, and 0.1949 for the SWH prediction in the future 1, 3, 6, 12, and 18 h. It can be used as a rapid SWH prediction system to ensure navigation safety to a certain extent, which has great practical significance and application value.

show abstract

Section: Related Workmentioning

confidence: 99%

Prediction of significant wave height based on EEMD and deep learning

Song

Wang

Huo³

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

show abstract

“…The GRU model architecture is shown in Figure 5. The update gate helps the GRU model determine how much past information needs to be passed into the future, as shown in Equation (7).…”

Section: Gated Recurrent Unitmentioning

confidence: 99%

“…Numerous techniques to wave height prediction have been presented, including machine learning, soft computing, and numerical methods [6]. Unlike machine learning, the numerical method's approach usually requires a high computational cost to produce good wave prediction, which requires an affordable computational cost [7]. Several works on wave height prediction have been published in the literature, employing a machine learning approach because it can efficiently map large data sets to suitable forecasts and has been widely used for forecasting in recent times [8].…”

Section: Introductionmentioning

confidence: 99%

Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM

Alfredo

Adytia

2022

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

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.

show abstract

“…However, the inherently non‐linear and non‐stationary nature of ocean waves poses a challenge to short‐term SWH forecasting. Existing numerical models like WAM [10], simulating waves nearshore [11], and WAVEWATCH‐III [12], while effective, often demand excessive computational resources, limiting their application to medium‐ and long‐term forecasting [13]. In response, alternative approaches such as autoregressive moving averages [14] and seasonal autoregressive integrated moving averages [15] have been explored.…”

Section: Introductionmentioning

confidence: 99%

An integrated methodology for significant wave height forecasting based on multi‐strategy random weighted grey wolf optimizer with swarm intelligence

Dokur,

Erdogan,

Salari

et al. 2024

IET Renewable Power Gen

View full text Add to dashboard Cite

While wave energy is regarded as one of the prominent renewable energy resources to diversify global low‐carbon generation capacity, operational reliability is the main impediment to the wide deployment of the related technology. Current experience in wave energy systems demonstrates that operation and maintenance costs are dominant in their cost structure due to unplanned maintenance resulting in energy production loss. Accurate and high performance simulation forecasting tools are required to improve the efficiency and safety of wave converters. This paper proposes a new methodology for significant wave height forecasting. It is based on incorporating swarm decomposition (SWD) and multi‐strategy random weighted grey wolf optimizer (MsRwGWO) into a multi‐layer perceptron (MLP) forecasting model. This approach takes advantage of the SWD approach to generate more stable, stationary, and regular patterns of the original signal, while the MsRwGWO optimizes the MLP model parameters efficiently. As such, forecasting accuracy has improved. Real wave datasets from three buoys in the North Atlantic Sea are used to test and validate the forecasting performance of the proposed model. Furthermore, the performance is evaluated through a comparison analysis against deep‐learning based state‐of‐the‐art forecasting models. The results show that the proposed approach significantly enhances the model's accuracy.

show abstract

Significant wave height forecasting using long short-term memory neural network in Indonesian waters

Cited by 11 publications

References 20 publications

Prediction of significant wave height based on EEMD and deep learning

Prediction of significant wave height based on EEMD and deep learning

Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM

An integrated methodology for significant wave height forecasting based on multi‐strategy random weighted grey wolf optimizer with swarm intelligence

Contact Info

Product

Resources

About