Study of the Performance of Deep Learning Methods Used to Predict Tidal Current Movement

• Published in: Journal of marine science and engineering Vol. 11; no. 1; p. 26
• Main Authors: Zhang, Kai, Wang, Xiaoyong, Wu, He, Zhang, Xuefeng, Fang, Yizhou, Zhang, Lianxin, Wang, Haifeng
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2023
• Subjects: Accuracy; Algorithms; Artificial intelligence; Comparative analysis; Computer simulation; Correlation coefficient; Correlation coefficients; Current prediction; Data mining; Deep learning; Energy; Energy development; Energy sources; Force and energy; Kalman filters; Learning algorithms; Long short-term memory; Machine learning; Mathematical models; Methods; Multilayer perceptrons; Neural networks; Numerical analysis; numerical simulation; Ocean currents; Ocean energy resources; Prediction models; Propagation; Renewable resources; Simulation; Simulation methods; Statistical methods; Technology application; tidal current energy assessment; tidal current prediction; Tidal currents; Tidal energy; Tidal flow; Tidal power; Time series; Turbines; Velocity; Wavelet transforms; South China Sea; China

To predict tidal current movement accurately is essential in the process of tidal energy development. However, the existing methods have limits to meet the need for accuracy. Recently, artificial intelligence technology has been widely applied to solve this problem. In this paper, a tidal current pr...