Developing an expert system for predicting alluvial channel geometry using ANN

Riahi-Madvar, Hossien; Ayyoubzadeh, Seyed Ali; Atani, Mina Gholizadeh

doi:10.1016/j.eswa.2010.06.047

Cited by 39 publications

(12 citation statements)

References 59 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the main advantage of using an ANN model is that it does not require knowledge of the governing equation of complex physical and chemical systems that underlay process. When designing an ANN model, we must choose a proper learning algorithm, number of layers, number of nodes in each layer, and the nature of transfer functions …”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…In the first stage, to identify the most promising optimal networks, the coefficient of determination (R 2 ), the statistical accuracy measures such as the root mean squared of error (RMSE), and the sum of squared error (SSE) on both training and testing data sets were used. These statistical indicators can be shown mathematically as follows

R^{2} = 1 - \frac{\sum_{i = 1}^{N} {(t_{p k} - z_{p k})}^{2}}{\sum_{i = 1}^{N} {(t_{p k} - \bar{t_{p k}})}^{2}}

R M S E = \sqrt{\frac{\sum_{k = 1}^{N} (t_{p k} - z_{p k} {false)}^{2}}{N}}

S S E = \frac{\sum_{k = 1}^{N} {false(t_{p k} - z_{p k} false)}^{2}}{N}

where t pk and z pk are the actual and predicted values respectively, N is the total number of data sets, and

\bar{t_{p k}}

is the mean of t pk values.…”

Section: Data Processingmentioning

confidence: 99%

“…When designing an ANN model, we must choose a proper learning algorithm, number of layers, number of nodes in each layer, and the nature of transfer functions. [16] In this study, one hidden layer neural model was developed to predict the photocatalysis efficiency. Figure 1 shows the structure of a developed model including an input layer, a hidden layer, and an output layer.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of photocatalytic activity of immobilized titania nanoparticles by support vector machine and artificial neural network

et al. 2015

View full text Add to dashboard Cite

In this study, TiO2 nanoparticles immobilized on sackcloth fibre were used for the photodegradation of acid dye, and the efficiency of heterogeneous photocatalysts was predicted using the support vector machines model and artificial neural network model. Acid Red 73 was applied as a model compound. The experimental results were determined as the function of key factors such as initial H2O2 concentration, dye concentration, dissolved anions, pH, and time. The obtained results were used for training the models. To find the most suitable and reliable network, different algorithms and transfer functions were tested. The trial and error method was used to find the optimum number of neurons and layers. The root mean squared of error (RMSE), the sum of square error (SSE), and R2 for the models were calculated. Results show that support vector machines and neural network models can effectively learn and model the aforementioned process and predict the efficiency of photodegradation of coloured wastewater.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

R^{2} = 1 - \frac{\sum_{i = 1}^{N} {(t_{p k} - z_{p k})}^{2}}{\sum_{i = 1}^{N} {(t_{p k} - \bar{t_{p k}})}^{2}}

R M S E = \sqrt{\frac{\sum_{k = 1}^{N} (t_{p k} - z_{p k} {false)}^{2}}{N}}

S S E = \frac{\sum_{k = 1}^{N} {false(t_{p k} - z_{p k} false)}^{2}}{N}

where t pk and z pk are the actual and predicted values respectively, N is the total number of data sets, and

\bar{t_{p k}}

is the mean of t pk values.…”

Section: Data Processingmentioning

confidence: 99%

Section: Artificial Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of photocatalytic activity of immobilized titania nanoparticles by support vector machine and artificial neural network

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Some research has exploited the sensitivity of hydrological responses to variability in rainfall (Anquetin et al, ; Moreno, Valero‐Garcés, González‐Sampériz, & Rico, ; Zoccatelli, Borga, Chirico, & Nikolopoulos, ) and has demonstrated channel responses to extreme flood pulses through natural experiment statistics or remote sensing (Bauch & Hickin, ; Harrison, Pike, & Boughton, ; Kiss & Blanka, ). A few studies have evaluated the potential to simulate regime channel geometries using artificial neural networks (Riahi‐Madvar, Ayyoubzadeh, & Atani, ) but have rarely provided a mechanistic account of how fluvial relationships can prevent environmental degradation and improve project performance in the planning and design of flood channels.…”

Section: Introductionmentioning

confidence: 99%

A study of the stochastic evolution of hydraulic geometry relationships

Song

Zhong

Wang

2019

River Research & Apps

View full text Add to dashboard Cite

Uncertainty resulting from climatic and environmental changes creates barriers to the accurate acquisition of information about rivers. In this study, a set of stable stochastic differential equations is developed to simulate the dynamic probability distributions of typical hydraulic geometry variables represented by slope, width, depth, and velocity with variations in bankfull discharge over time for a river system. Random parts of the

show abstract

“…Therefore, ANN is increasingly becoming a practical tool to predict different phenomena of engineering. This artificial intelligence method has been successfully used to predict the hydraulic engineering applications, such as flow field (Benning et al, 2001), critical submergence of an intake in still water and open channel flow (Kocabas et al, 2008), backwater through bridge constrictions (Seckin et al, 2009 andPinar et al, 2010), the friction factor of open channel flow (Yuhong and Wenxin, 2009), discharge capacity of straight compound channels (Unal et al, 2010), alluvial channel geometry (Riahi-Madvar et al, 2011), equilibrium scour depth around hydraulic structures (Keshavarzi et al, 2012 andKarami et al, 2012) and the length of hydraulic jumps (Naseri and Othman, 2012). A few studies have been performed on the prediction of the lateral outflow over triangular labyrinth and rectangular side weirs located on straight and curved channels Bilhan et al (2010Bilhan et al ( , 2011 and Kisi et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

Discharge prediction of circular and rectangular side orifices using artificial neural networks

et al. 2015

View full text Add to dashboard Cite

A side orifice created in the side of a channel is a structure for diverting some of the flow from the main channel for different purposes. The prediction of the discharge through this side structure is very important in hydraulic and irrigation engineering. In the present study, three artificial neural network models including feed forward back propagation, radial basis function, and Generalized Regression neural networks as well as a multiple non-linear regression method were used to predict the discharge coefficient for flow through both square and circular shapes of sharp-crested side orifices. The discharge coefficient was modeled as a function of five input non-dimensional variables resulted from five dimensional variables, which were the type of orifice shape, the diameter or width of the orifice, crest height, depth and velocity of approach flow. The results obtained in this study indicated that all of the neural network models could successfully predict the discharge coefficient with adequate accuracy. However, according to different performance measures, the accuracy of radial basis function approach was a bit better than two other neural network models. The neural network models predicted the discharge coefficient more accurately than the non-linear regression relation.

show abstract

Developing an expert system for predicting alluvial channel geometry using ANN

Cited by 39 publications

References 59 publications

Evaluation of photocatalytic activity of immobilized titania nanoparticles by support vector machine and artificial neural network

Evaluation of photocatalytic activity of immobilized titania nanoparticles by support vector machine and artificial neural network

A study of the stochastic evolution of hydraulic geometry relationships

Discharge prediction of circular and rectangular side orifices using artificial neural networks

Contact Info

Product

Resources

About