Wave Height Estimation From X-Band Nautical Radar Images Using Temporal Convolutional Network

In this article, a temporal convolutional network (TCN)-based model is proposed to retrieve significant wave height (<inline-formula><tex-math notation="LaTeX">$H_s$</tex-math></inline-formula>) from X-band nautical radar images. Three types of features are first ex...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Weimin Huang, Zhiding Yang, Xinwei Chen
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/fab7438fd7534d46837baaaa5507f28a
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:In this article, a temporal convolutional network (TCN)-based model is proposed to retrieve significant wave height (<inline-formula><tex-math notation="LaTeX">$H_s$</tex-math></inline-formula>) from X-band nautical radar images. Three types of features are first extracted from radar image sequences based on signal-to-noise ratio (SNR), ensemble empirical mode decomposition (EEMD), and gray level cooccurrence matrix methods, respectively. Then, feature vectors are input into the proposed TCN-based regression model to produce <inline-formula><tex-math notation="LaTeX">$H_s$</tex-math></inline-formula> estimation. Radar data are collected from a moving vessel at the East Coast of Canada, as well as the simultaneous wave data measured by several wave buoys deployed nearby are used for model training and testing. Experimental results after averaging show that TCN-based model further improves the <inline-formula><tex-math notation="LaTeX">$H_s$</tex-math></inline-formula> estimation accuracy, with reductions of root-mean-square errors by 0.33 and 0.10 m, respectively, compared to the SNR-based and the EEMD-based linear fitting methods. It has also been found that under the same feature extraction scheme, TCN outperforms other machine learning-based algorithms including support vector regression and the gated recurrent unit network.