Forecasting local mean sea level by generalized behavioral learning method

Yükleniyor...
Küçük Resim

Tarih

2017-03-13

Dergi Başlığı

Dergi ISSN

Cilt Başlığı

Yayıncı

Springer Nature

Erişim Hakkı

info:eu-repo/semantics/closedAccess
Attribution-NonCommercial-ShareAlike 3.0 United States

Özet

Determining and forecasting the local mean sea level (MSL), which is a major indicator of global warming, is an essential issue to set public policies to save our future. Owing to its importance, MSL values are measured and shared periodically by many agencies. It is not easy to model or forecast MSL because it depends on many dynamic sources such as global warming, geophysical phenomena, and circulations in the ocean and atmosphere. Several of researchers applied and recommended employing artificial neural network (ANN) in the estimation of MSL. However, ANN does not take into account the order of samples, which may consist essential information. In this study, the generalized behavioral learning method (GBLM), which is based on behavioral learning theories, was employed in order to achieve higher accuracies by using samples in the training dataset and the order of samples. To evaluate and validate GBLM, MSL of seven stations around the world was picked up. These datasets were employed to forecast the local MSL for the future. Obtained results were compared with the ones obtained by ANN that is trained by extreme learning machine and the literature. The GBLM is found to be successful in terms of the achieved high accuracies and the ability to tracking trends and fluctuations of a local MSL.

Açıklama

Anahtar Kelimeler

Extreme Learning Machine, Generalized Behavioral Learning Method, Mean Sea Level, PSMSL Database

Kaynak

WoS Q Değeri

Q2

Scopus Q Değeri

Q1

Cilt

42

Sayı

8

Künye

Ertuğrul, Ö F., Tağluk, M. E. (2017). Forecasting local mean sea level by generalized behavioral learning method. Arabian Journal for Science and Engineering, 42(8), pp. 3289-3298. https://doi.org/10.1007/s13369-017-2468-4