Data pre-processing and artificial neural networks for tidal level prediction at the Pearl River Estuary

Traditionally, tidal level is predicted by harmonic analysis (HA). In this paper, three hybrid models that couple varied pre-processing methods, which are empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and empirical wavelet transform (EWT), with the nonlinear autor...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bing-Xian Liang, Jin-Peng Hu, Cheng Liu, Bo Hong
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	eemd emd ewt harmonic analysis narx tidal level prediction Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066
Acceso en línea:	https://doaj.org/article/b20b356ae36443f8aeec1c324b36e4c8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b20b356ae36443f8aeec1c324b36e4c8
record_format	dspace
spelling	oai:doaj.org-article:b20b356ae36443f8aeec1c324b36e4c82021-11-05T17:43:07ZData pre-processing and artificial neural networks for tidal level prediction at the Pearl River Estuary1464-71411465-173410.2166/hydro.2020.055https://doaj.org/article/b20b356ae36443f8aeec1c324b36e4c82021-03-01T00:00:00Zhttp://jh.iwaponline.com/content/23/2/368https://doaj.org/toc/1464-7141https://doaj.org/toc/1465-1734Traditionally, tidal level is predicted by harmonic analysis (HA). In this paper, three hybrid models that couple varied pre-processing methods, which are empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and empirical wavelet transform (EWT), with the nonlinear autoregressive networks with exogenous inputs (NARX) were applied to forecast tidal level. The models were, namely, EMD-NARX, EEMD-NARX, and EWT-NARX. The sub-series obtained by using EMD or EEMD or EWT were then used as the input vectors to the NARX with the original data as targets. Notably, the EWT-NARX model was employed to predict the tidal level for the first time. Simulations were based on the measurements from four tidal stations at the Pearl River Estuary, China. The results showed that the EWT-NARX, EEMD-NARX, and EMD-NARX outperformed the HA model. Specifically, EWT-NARX was optimal among the four. Moreover, from the Hilbert energy spectra we can see the EWT solved the mode-mixing problem that EMD and EEMD suffered from, thus enabling precise tidal level prediction. Simulations and experimental results confirmed that the EWT-NARX model can achieve prediction of the tidal level with high accuracy. HIGHLIGHTS EWT-NARX model was applied to predict the tidal level for the first time.; EWT-NARX outperformed EEMD-NARX, EMD-NARX, and harmonic analysis.; EWT solves the mode-mixing problem that EMD and EEMD suffered so that the EWT-NARX model has better prediction performance.;Bing-Xian LiangJin-Peng HuCheng LiuBo HongIWA Publishingarticleeemdemdewtharmonic analysisnarxtidal level predictionInformation technologyT58.5-58.64Environmental technology. Sanitary engineeringTD1-1066ENJournal of Hydroinformatics, Vol 23, Iss 2, Pp 368-382 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	eemd emd ewt harmonic analysis narx tidal level prediction Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066
spellingShingle	eemd emd ewt harmonic analysis narx tidal level prediction Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066 Bing-Xian Liang Jin-Peng Hu Cheng Liu Bo Hong Data pre-processing and artificial neural networks for tidal level prediction at the Pearl River Estuary
description	Traditionally, tidal level is predicted by harmonic analysis (HA). In this paper, three hybrid models that couple varied pre-processing methods, which are empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and empirical wavelet transform (EWT), with the nonlinear autoregressive networks with exogenous inputs (NARX) were applied to forecast tidal level. The models were, namely, EMD-NARX, EEMD-NARX, and EWT-NARX. The sub-series obtained by using EMD or EEMD or EWT were then used as the input vectors to the NARX with the original data as targets. Notably, the EWT-NARX model was employed to predict the tidal level for the first time. Simulations were based on the measurements from four tidal stations at the Pearl River Estuary, China. The results showed that the EWT-NARX, EEMD-NARX, and EMD-NARX outperformed the HA model. Specifically, EWT-NARX was optimal among the four. Moreover, from the Hilbert energy spectra we can see the EWT solved the mode-mixing problem that EMD and EEMD suffered from, thus enabling precise tidal level prediction. Simulations and experimental results confirmed that the EWT-NARX model can achieve prediction of the tidal level with high accuracy. HIGHLIGHTS EWT-NARX model was applied to predict the tidal level for the first time.; EWT-NARX outperformed EEMD-NARX, EMD-NARX, and harmonic analysis.; EWT solves the mode-mixing problem that EMD and EEMD suffered so that the EWT-NARX model has better prediction performance.;
format	article
author	Bing-Xian Liang Jin-Peng Hu Cheng Liu Bo Hong
author_facet	Bing-Xian Liang Jin-Peng Hu Cheng Liu Bo Hong
author_sort	Bing-Xian Liang
title	Data pre-processing and artificial neural networks for tidal level prediction at the Pearl River Estuary
title_short	Data pre-processing and artificial neural networks for tidal level prediction at the Pearl River Estuary
title_full	Data pre-processing and artificial neural networks for tidal level prediction at the Pearl River Estuary
title_fullStr	Data pre-processing and artificial neural networks for tidal level prediction at the Pearl River Estuary
title_full_unstemmed	Data pre-processing and artificial neural networks for tidal level prediction at the Pearl River Estuary
title_sort	data pre-processing and artificial neural networks for tidal level prediction at the pearl river estuary
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/b20b356ae36443f8aeec1c324b36e4c8
work_keys_str_mv	AT bingxianliang datapreprocessingandartificialneuralnetworksfortidallevelpredictionatthepearlriverestuary AT jinpenghu datapreprocessingandartificialneuralnetworksfortidallevelpredictionatthepearlriverestuary AT chengliu datapreprocessingandartificialneuralnetworksfortidallevelpredictionatthepearlriverestuary AT bohong datapreprocessingandartificialneuralnetworksfortidallevelpredictionatthepearlriverestuary
_version_	1718444120345673728

Data pre-processing and artificial neural networks for tidal level prediction at the Pearl River Estuary

Ejemplares similares