Enhancing the Predicting Accuracy of the Water Stage Using a Physical-Based Model and an Artificial Neural Network-Genetic Algorithm in a River System

Abstract

Accurate simulations of river stages during typhoon events are critically important for flood control and are necessary for disaster prevention and water resources management in Taiwan. This study applies two artificial neural network (ANN) models, including the back propagation neural network (BPNN) and genetic algorithm neural network (GANN) techniques, to improve predictions from a one-dimensional flood routing hydrodynamic model regarding the water stages during typhoon events in the Danshuei River system in northern Taiwan. The hydrodynamic model is driven by freshwater discharges at the upstream boundary conditions and by the water levels at the downstream boundary condition. The model provides a sound physical basis for simulating water stages along the river. The simulated results of the hydrodynamic model show that the model cannot reproduce the water stages at different stations during typhoon events for the model calibration and verification phases. The BPNN and GANN models can improve the simulated water stages compared with the performance of the hydrodynamic model. The GANN model satisfactorily predicts water stages during the training and verification phases and exhibits the lowest values of mean absolute error, root-mean-square error and peak error compared with the simulated results at different stations using the hydrodynamic model and the BPNN model. Comparison of the simulated results shows that the GANN OPEN ACCESSWater 2014, 6 1643 model can be successfully applied to predict the water stages of the Danshuei River system during typhoon events.

Genetic Algorithm-Based Fuzzy Comprehensive Evaluation of Water Quality in Dongzhaigang

“…The current processing method lacks underlying scientific theory and method. To compensate for the disadvantages of the current method, the genetic algorithm is introduced into the fuzzy comprehensive evaluation method to amend the consistency of the judging matrix and to calculate the weight of each evaluation index [13][14][15][45][46][47]. Comprehensive evaluation quantified indexes reflect the assessed objects by establishing subsets, and the evaluation results are obtained by integrating all indexes with a transform principal.…”

Soft Measurement Modeling Based on Chaos Theory for Biochemical Oxygen Demand (BOD)

“…The neural network model with chaos theory is written as C-ANN. The ANNs which are used for comparison include multilayer perceptron (MLP) [14], radial basis function neural network (RBF) [7], Elman neural network (Elman), fuzzy neural network (FNN) [1], MLP with chaos theory (C-MLP), RBF with chaos theory (C-RBF), Elman with chaos theory (C-Elman), and FNN with chaos theory (C-FNN). All ANNs adopt the traditional gradient descent method for training all connection weights.…”

“…Artificial neural network (ANN) has some particular properties such as large scale parallel distributed processing, fault-tolerance, self-organized learning, classification, self-adaptation and strong capability of the nonlinear approximation with high reconstructing accuracy and fast training rate for the nonlinear dynamic system [7,8]. Therefore, models based on ANN which can mirror the law hidden in the data are the most popular ones for the soft measurement modeling and prediction [9].…”

Daily Reservoir Runoff Forecasting Method Using Artificial Neural Network Based on Quantum-behaved Particle Swarm Optimization

“…However, when PSO is applied for the ANN parameters selection, it may be trapped into the local optima of the objective function because PSO is restricted by search capability. Therefore, the promotion space is still large for ANN parameter selection using an evolutionary algorithm [22][23][24].…”