The potential of different ANN techniques in evapotranspiration modelling

Engineering Applications of Computational Fluid Mechanics

et al. 2016

A modified multi-layer perceptron (MLP) model based on decision trees (DT-MLP) is presented to predict velocity and water free-surface profiles in a 90°open-channel bend. The ability of the new hybrid model to predict the velocity and flow depth in a 90°sharp bend is investigated and compared with the abilities of MLP and multiple-linear regression (MLR) models. The MLP and DT-MLP networks are trained and tested using 520 and 506 experimental data measured for velocity and flow depth, respectively, at five different discharge rates of 5, 7.8, 13.6, 19.1 and 25.3 l/s. The MLP and DT-MLP comparison results against MLR reveal that the two artificial neural networks (ANNs) are 84% and 16% more accurate than the MLR model in predicting the velocity and flow depth variables, respectively. According to the results, the root mean square error (RMSE) value of the DT-MLP model decreases by 9% and 7.5% in predicting velocity and flow depth, respectively, compared with the MLP model. It was found that the hybrid decision-tree-based method can significantly improve MLP neural network performance in forecasting velocity and free-surface profiles in a 90°open-channel bend. ARTICLE HISTORY

Section: Multi-layer Perceptron (Mlp) Neural Networkmentioning

confidence: 99%

Design of modified structure multi-layer perceptron networks based on decision trees for the prediction of flow parameters in 90° open-channel bends

Gholami

Engineering Applications of Computational Fluid Mechanics

et al. 2016

“…However, there is no definitive rule to determine the number of hidden layer neurons. In this study, trial and error is used to determine the number of hidden layer neurons in the MLP models employed (Bilhan et al, 2010;Breiman et al, 1993;Kisi, 2008). …”

Section: Multi-layer Perceptron Neural Networkmentioning

confidence: 99%

Design of a new hybrid artificial neural network method based on decision trees for calculating the Froude number in rigid rectangular channels

Ebtehaj

Journal of Hydrology and Hydromechanics

et al. 2016

A vital topic regarding the optimum and economical design of rigid boundary open channels such as sewers and drainage systems is determining the movement of sediment particles. In this study, the incipient motion of sediment is estimated using three datasets from literature, including a wide range of hydraulic parameters. Because existing equations do not consider the effect of sediment bed thickness on incipient motion estimation, this parameter is applied in this study along with the multilayer perceptron (MLP), a hybrid method based on decision trees (DT) (MLP-DT), to estimate incipient motion. According to a comparison with the observed experimental outcome, the proposed method performs well (MARE = 0.048, RMSE = 0.134, SI = 0.06, BIAS = -0.036). The performance of MLP and MLP-DT is compared with that of existing regression-based equations, and significantly higher performance over existing models is observed. Finally, an explicit expression for practical engineering is also provided.

“…However, if the number of hidden layer neurons is excessively high, the model will undergo overtraining and memorize the data instead of analyzing them. The number of neurons within the hidden layer(s) is commonly determined through trial and error (Cobaner, Unal, & Kisi, 2009;Kalteh, 2008;Kisi, 2008;Zaji & Bonakdari, 2015). Therefore, the trial and error method was utilized and different models were tested with various numbers of neurons considered within the hidden layer.…”

Section: Ann Structurementioning

confidence: 99%

Simulation of open channel bend characteristics using computational fluid dynamics and artificial neural networks

Gholami

Engineering Applications of Computational Fluid Mechanics

et al. 2015

The ability to simulate flow characteristics is one of the most important issues in the design and application of open channel bends. Three-dimensional computational fluid dynamics (CFD) and multi-layer feed-forward artificial neural networks (MLFF-ANNs) are used and compared in modeling the flow depth and velocity field in sharp bends. CFD is modeled in two phases, water and air, using the volume of fluid method. The backpropagation algorithm is applied in the training process of the ANN model. An experimental study of a 90°curved channel is undertaken to verify and compare the efficiency of the CFD and ANN models. The results show that both CFD and ANN methods can be successfully applied to the modeling of open channel bend characteristics. However, the ANN method performs significantly better than CFD.