Decision Tree–Based Classifier Combined with Neural-Based Predictor for Water-Stage Forecasts in a River Basin During Typhoons: A Case Study in Taiwan

Abstract

To solve the complicated problem of water-stage predictions under the interaction of upstream flows and tidal effects during typhoon attacks, this article presents a novel approach to river-stage predictions. The proposed CART-ANN model combines both the decision trees (classification and regression trees [CART]) and the artificial neural network (ANN) techniques, which comprise the multilayer perceptron (MLP) and radial basis function (RBFNN). The combined CART-ANN model involves a two-step predicting process. First, the CART stage-level classifier can classify the river stages into higher, middle, and lower levels. Then, the ANN-based water-stage predictors are employed to predict the water stages. The proposed model was applied to the Tanshui River Basin in Taiwan. The Taipei Bridge, which is close to the estuary and affected by tidal effects, was taken as the study gauge. The mean square error and the mean absolute error were used for evaluating the variance and bias performances of the models. This study makes two contributions. First, the CART-MLP and CART-RBF were modeled to predict river stages under tidal effects during typhoons, and they were compared with three benchmark models, CART, back-propagation neural network, and RBFNN. Second, the CART-RBF successfully demonstrated that it achieved more accurate prediction than CART-MLP and three benchmark models.

Evaluation of Photovoltaic Power Generation by Using Deep Learning in Solar Panels Installed in Buildings

“…The simulation results of the DNN model were compared with those of the benchmark models (i.e., BPN and LR models) to verify its quality. A typical BPN, which is a shallow neural network, with three layers (i.e., an input layer, a hidden layer, and an output layer) is a feedforward neural network trained with the standard backpropagation algorithm [68]. Figure 7 illustrates the scatter diagrams of the predicted and observed values of DNN, BPN, and LR.…”

Radial basis neural tree model for improving waste recovery process in a paper industry

“…The RBFN theory has been applied to various problems, such as estimation, prediction, and/or classification problems in previous literature . To harness the advantages of single models, several previous studies are concentrated on the hybridization of RT and ANN models, namely, entropy nets and neural tree, and various others …”

“…[19][20][21] To harness the advantages of single models, several previous studies are concentrated on the hybridization of RT and ANN models, namely, entropy nets 22 and neural tree, 23 and various others. [24][25][26][27][28][29][30] Motivated by the above discussion, we have proposed a radial basis neural tree (RBNT) model that utilizes the power of both the tree-based models and ANNs to solve the production process efficiency problem. In the hybridization, we have used RTs as a feature selection algorithm and utilized RT given features along with RT predicted values as input features in the RBFN model.…”

Comparing lazy and eager learning models for water level forecasting in river-reservoir basins of inundation regions

“…Numerous eager learning models have been developed to solve various problems. Since the resurgence of ANNs in the late 1980s (begun by the introduction of the backpropagation training algorithm for feedforward ANNs), ANNs have become the preferred prediction approach, applied widely in flow routing and river-stage forecasting (e.g., Liong et al, 2000;Maier and Dandy, 2000;Kerh and Lee, 2006;Altunkaynak, 2007;Ondimu and Murase, 2007;Lin et al, 2010;Alvisi and Franchini, 2011;Tsai et al, 2012;Wolfs and Willems, 2014). The value of ANNs is that feedforward networks (such as multilayer perceptrons, MLP) are universal approximators and can learn any continuous functions with arbitrary accuracy.…”