A Deep Learning Approach for Wave Forecasting Based on a Spatially Correlated Wind Feature, with a Case Study in the Java Sea, Indonesia

Abstract

For safety and survival at sea and on the shore, wave predictions are essential for marine-related activities, such as harbor operations, naval navigation, and other coastal and offshore activities. In general, wave height predictions rely heavily on numerical simulations. The computational cost of such a simulation can be very high (and it can be time-consuming), especially when considering a complex coastal area, since these simulations require high-resolution grids. This study utilized a deep learning technique called bidirectional long short-term memory (BiLSTM) for wave forecasting to save computing time and to produce accurate predictions. The deep learning method was trained using wave data obtained by a continuous numerical wave simulation using the SWAN wave model over a 20-year period with ECMWF ERA-5 wind data. We utilized highly spatially correlated wind as input for the deep learning method to select the best feature for wave forecasting. We chose an area with a complex geometry as the study case, an area in Indonesia’s Java Sea. We also compared the results of wave prediction using BiLSTM with those of other methods, i.e., LSTM, support vector regression (SVR), and a generalized regression neural network (GRNN). The forecasting results using the BiLSTM were the best, with a correlation coefficient of 0.96 and an RMSE value of 0.06.

Machine Learning‐Based Wave Model With High Spatial Resolution in Chesapeake Bay

“…Unlike other ML wave models applied at a single station or selected limited stations (Adytia et al., 2022; Chen et al., 2021; Wang et al., 2023), we employed a dimensionality reduction approach to transform the high‐dimensional data into a lower‐dimensional space, and therefore, we only trained the temporal principal components. Although this approach will introduce model errors using limited PCs, the approach allows the model to predict wave heights in high spatial resolution.…”

“…For this study, the data model did not include coastal areas as our focus is inside the bay. There are several applications of ML for downscale wave models (Adytia et al., 2022; Michel et al., 2022) using different methods. We believe that our approach can be applied to open coastal as well.…”

An Entity of the Ocean Data Prediction System Using Machine Learning Techniques

“…A machine-learning-based prediction approach are provided and validated using simulated data from the two-dimensionally complicated Ginzburg-Landau equation and real wind speed data from the North Atlantic Ocean [8]. Discussed are the trade-offs between forecast accuracy, spatial resolution, and prediction horizon, as well as how catastrophic event incidence that is geographically skewed impacts forecast accuracy.…”

A New Deep Learning Restricted Boltzmann Machine for Energy Consumption Forecasting

“…As a result, planning should be performed while considering reliability coefficients and the maximum load. Until future development, the planned network must also satisfy the demands of the area [3,4].…”