Application of neural networks and fuzzy logic models to long-shore sediment transport

TY - JOUR

T1 - Application of neural networks and fuzzy logic models to long-shore sediment transport

AU - Kabiri-Samani, A. R.

AU - Aghaee-Tarazjani, J.

AU - Borghei, S. M.

AU - Jeng, D. S.

N1 - dc.publisher: Elsvier

PY - 2011/3

Y1 - 2011/3

N2 - Predictions of long-shore sediment transport rate (LSTR) are a vital task for coastal engineers in the determination of erosion or accretion along coasts. Many scientists have tried to find empirical method for the estimation of LSTR in the past decades. However, due to the influence of significant number of parameters and randomness of the data, the existing empirical methods provide quite different results and have limited applications. In this paper, an alternative approach, fuzzy logic and neural network, is proposed to estimate LSTR. Six dominant variables on LSTR are considered in the present models, including wave breaking height (Hbs), wave period (T), wave breaking angle (abs), beach slope (m), grain size (D) and sediment mass flow rate along shore (Qs). A comprehensive comparison between both neural networks and fuzzy logic models and the existing empirical formulae will be presented to demonstrate capacity of fuzzy logic and artificial neural network.

AB - Predictions of long-shore sediment transport rate (LSTR) are a vital task for coastal engineers in the determination of erosion or accretion along coasts. Many scientists have tried to find empirical method for the estimation of LSTR in the past decades. However, due to the influence of significant number of parameters and randomness of the data, the existing empirical methods provide quite different results and have limited applications. In this paper, an alternative approach, fuzzy logic and neural network, is proposed to estimate LSTR. Six dominant variables on LSTR are considered in the present models, including wave breaking height (Hbs), wave period (T), wave breaking angle (abs), beach slope (m), grain size (D) and sediment mass flow rate along shore (Qs). A comprehensive comparison between both neural networks and fuzzy logic models and the existing empirical formulae will be presented to demonstrate capacity of fuzzy logic and artificial neural network.

KW - Fuzzy logic

KW - Long-Shore

KW - Sedimentation

KW - Neural networks

U2 - 10.1016/j.asoc.2010.11.021

DO - 10.1016/j.asoc.2010.11.021

M3 - Article

SN - 1568-4946

VL - 11

SP - 2880

EP - 2887

JO - Applied Soft Computing

JF - Applied Soft Computing

IS - 2

ER -