Bidirectional Modeling of Surface Winds and Significant Wave Heights in the Caribbean Sea

Abstract

Though the ocean is sparsely populated by buoys that feature co-located instruments to measure surface winds and waves, their data is of vital importance. However, due to either minor instrumentation failure or maintenance, intermittency can be a problem for either variable. This paper attempts to mitigate the loss of valuable data from two opposite but equivalent perspectives: the conventional reconstruction of significant wave height (SWH) from Caribbean Sea buoy-observed surface wind speeds (WSP) and the inverse modeling of WSP from SWH using the long short-term memory (LSTM) network. In either direction, LSTM is strongly able to recreate either variable from its counterpart with the lowest correlation coefficient (r2) measured at 0.95, the highest root mean square error (RMSE) is 0.26 m/s for WSP, and 0.16 m for SWH. The highest mean absolute percentage errors (MAPE) for WSP and SWH are 1.22% and 5%, respectively. Additionally, in the event of complete instrument failure or the absence of a buoy in a specific area, the Simulating WAves Nearshore (SWAN) wave model is first validated and used to simulate mean and extreme SWH before, during, and after the passage of Hurricane Matthew (2016). Synthetic SWH is then fed to LSTM in a joint SWAN—LSTM model, and the corresponding WSP is reconstructed and compared with observations. Although the reconstruction is highly accurate (r2 > 0.9, RMSE < 1.3 m/s, MAPE < 0.8%), there remains great room for improvement in minimizing error and capturing high-frequency events.

Improving Significant Wave Height Forecasts Using a Joint Empirical Mode Decomposition–Long Short-Term Memory Network

“…Although buoys are assumed to be ground truth, the errors of buoys in their measurements as they imperfectly record the wave state must be considered. Additionally, because intermittency forces the use of interpolation (as in this study) or the introduction of reanalysis or model data (as may be found in other studies, e.g., [31]), these methods are not a perfect representation of the wave state. Errors consequently creep naturally and unavoidably into the results, following compounding by EMD-LSTM's inherent errors, thus necessitating caution.…”

Recent Developments in Artificial Intelligence in Oceanography

“…In a similar study, Hu et al [90] used XGBoost and LSTM in the predictions of the significant wave height and peak wave period and found that XGBoost led to superior forecast results over LSTM, but both ran significantly faster than WW3. Bethel et al [91] showed that due to the strong causal link between significant wave heights and surface wind speeds, each can be forecasted from its counterpart with a high degree of accuracy, and this is even possible under extreme conditions, as may be forced by TCs. 9 Ocean-Land-Atmosphere Research Despite the aforementioned advances, the current accuracy and model training speed of prediction for oceanic variables using artificial intelligence (AI) techniques are still limited by the resolution and accuracy of labeled data.…”

Whitecap Fraction Parameterization and Understanding with Deep Neural Network

“…Fortunately, neural network-based parameterization can avoid complex physical modeling. With the development of computer hardware and software, neural networks have been successfully applied in many perspectives of marine sciences, such as the ocean element forecast [21,22] and ocean feature identification [23,24], attributable to their great ability to solve nonlinear problems. Meanwhile, attempts have been made to develop new parameterizations using neural networks to simulate complex atmospheric and oceanic processes more accurately, such as ocean mesoscale parameterization [25,26] and vertical mixing parameterization [27,28].…”