Comparison of neural networks and neuro-fuzzy computing techniques for prediction of peak breach outflow

Abstract

Accurate prediction of peak outflows from breached embankment dams is a key parameter in dam risk assessment. In this study, efficient models were developed to predict peak breach outflows utilizing artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). Historical data from 93 embankment dam failures were used to train and evaluate the applicability of these models. Two scenarios were applied with each model by either considering the whole data set without classification or classifying the set into small dams (48 dams) and large dams (45 dams). In this way, nine models were developed and their results were compared to each other and to the results of the best available regression equations and recent gene expression programming. Among the different models, the ANFIS model of the first scenario exhibited better performance based on its higher efficiency (E = 0.98), higher coefficient of determination (R2 = 0.98) and lower mean absolute error (MAE = 840.9). Moreover, models based on classified data enhanced the prediction of peak outflows particularly for small dams. Finally, this study indicated the potential of the developed ANFIS and ANN models to be used as predictive tools of peak outflow rates of embankment dams.

Evaluation of Three Evaporation Estimation Techniques In A Semi-Arid Region (Omar El Mukhtar Reservoir Sluge, Libya- As a case Study)

“…Artificial Neural Networks (ANN) , are a form of computing inspired by the functioning of the brain and nervous system, and discussed in detail in a number of hydrologic papers [9]. The feed forward ANN has been adopted in many hydrological modeling studies because of its applicability to a variety of different problems [4].…”

“…The Levenberg-Marquardt (LM) training algorithm is a trust region based method with a hyper-spherical trust region [9]. This algorithm was implemented in this study using the Neural Network Toolbox of MATLAB, an example of Developed Structure of ANN with input combination as in Figure 4.…”

A comprehensive evaluation method for concrete dam health state combined with gray-analytic hierarchy-optimization theory

“…In addition, some scholars selected fuzzy mathematics to evaluate dam health state and the diagnosis techniques mainly consisted of fuzzy cluster analysis, fuzzy comprehensive evaluation, and fuzzy pattern recognition. 13,14 Wu et al 15 suggested an overall framework for the comprehensive evaluation of dam health adopting pattern recognition and fuzzy evaluation. On the basis of fuzzy control theory and expert experience, Ma et al 16 utilized fuzzy comprehensive evaluation method to assess the health state of concrete dams.…”