Hourly significant wave height prediction via singular spectrum analysis and wavelet transform based models


Altunkaynak A., Çelik A., Mandev M. B.

Ocean Engineering, vol.281, 2023 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 281
  • Publication Date: 2023
  • Doi Number: 10.1016/j.oceaneng.2023.114771
  • Journal Name: Ocean Engineering
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Aerospace Database, Applied Science & Technology Source, Aquatic Science & Fisheries Abstracts (ASFA), Communication Abstracts, Computer & Applied Sciences, Environment Index, ICONDA Bibliographic, INSPEC, Metadex, Civil Engineering Abstracts
  • Keywords: Fuzzy logic, Hybrid model, Prediction, Significant wave height, Singular spectrum analysis, Wavelet transform
  • Istanbul Technical University Affiliated: Yes

Abstract

Generation of significant wave height (SWH) is considered as a complex and stochastic dynamical process whose prediction is vital for effective marine, ocean engineering, sustainable development and scientific phenomena. Based on literature review, despite numerous research attempts to forecast significant wave height with short prediction time horizons, they are incapable in yielding accurate SWH predictions. To achieve this end wavelet techniques have been intensively employed as data pre-processing tools and, have been incorporated with soft computing based approaches to improve the prediction performance of developed models. However, wavelet algorithm has some limitations such as shift sensitivity, poor directionality and lack of phase information. In addition, this technique suffers from time consuming complicated mathematical procedures. In the present study, as a way of addressing the shortcomings of wavelet tool and enhancing prediction accuracy with extended time horizons, singular spectrum analysis (SSA) is proposed as a decomposition procedure. The prediction accuracy of the three distinct models is contrasted by means of diagnostic metrics, Mean Square Error (MSE), the Nash-Sutcliffe Coefficient of efficiency (CE) and determination of coefficient (R2). With its lowest MSE and highest CE value SSA-Fuzzy model clearly outperformed the stand alone Fuzzy and W-Fuzzy models in predicting hourly SWH for all stations and future time horizons. This implies that SSA technique has the utmost capability to decompose measured data effectively into its deterministic and stochastic components.