Improved irrigation water demand forecasting using a soft-computing hybrid model

Pulido‐Calvo, Inmaculada; Gutiérrez‐Estrada, Juan Carlos

doi:10.1016/j.biosystemseng.2008.09.032

Cited by 125 publications

(30 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The TS model utilizes a combination of the least-square method and the back-propagation gradient descent method for training the FIS membership function parameters to identify patterns hidden in a given training dataset [19][20][21][22].…”

Section: Hybrid Algorithmmentioning

confidence: 99%

Computing Air Demand Using the Takagi–Sugeno Model for Dam Outlets

Zounemat‐Kermani

Scholz

2013

Water

View full text Add to dashboard Cite

An adaptive neuro-fuzzy inference system (ANFIS) was developed using the subtractive clustering technique to study the air demand in low-level outlet works. The ANFIS model was employed to calculate vent air discharge in different gate openings for an embankment dam. A hybrid learning algorithm obtained from combining back-propagation and least square estimate was adopted to identify linear and non-linear parameters in the ANFIS model. Empirical relationships based on the experimental information obtained from physical models were applied to 108 experimental data points to obtain more reliable evaluations. The feed-forward Levenberg-Marquardt neural network (LMNN) and multiple linear regression (MLR) models were also built using the same data to compare model performances with each other. The results indicated that the fuzzy rule-based model performed better than the LMNN and MLR models, in terms of the simulation performance criteria established, as the root mean square error, the Nash-Sutcliffe efficiency, the correlation coefficient and the Bias.

show abstract

Section: Hybrid Algorithmmentioning

confidence: 99%

Computing Air Demand Using the Takagi–Sugeno Model for Dam Outlets

Zounemat‐Kermani

Scholz

2013

Water

View full text Add to dashboard Cite

show abstract

“…Due to the high capacity of soft computing method to analyze complex problems, this method has been used extensively in various hydraulic engineering problems such as discharge capacity of lateral weirs (Neary, & Sotiropoulos, 1996;Bilhan, Emiroglu, & Kisi, 2011), scour depth prediction (Muzzammil, 2010), flow characteristics in different open channels (Donmez, 2001;Grace & Priest, 1958;More, 1978), rainfall modeling and stream flow prediction (Asadi, Shahrabi, Abbaszadeh, & Tabanmehr, 2013;Chau, Wu, & Li, 2005;Chen & Chau, 2006;Cheng, Lin, Sun, & Chau, 2005;Firat & Gungor, 2008;Wu, Chau, & Li, 2009;Yurtseven, & Zengin, 2013), modelling coastal algal blooms (Muttil & Chau, 2006), evapotranspiration (Cobaner, 2011;Kisi, & Ozturk, 2007), combined open channel flow (Hager, 1987), sediment transport (Ebtehaj, & Bonakdari, 2013;Van Maanen, Coco, Bryan, & Ruessink, 2010), ground water level prediction (Taormina, Chau, & Sethi, 2012) and water demand forecasting (Pulido-Calvo & Gutierrez-Estrada, 2009;Tiwari, & Adamowski, 2013).…”

Section: Introductionmentioning

confidence: 99%

Efficient methods for prediction of velocity fields in open channel junctions based on the artifical neural network

Zaji

Bonakdari

2015

Engineering Applications of Computational Fluid Mechanics

View full text Add to dashboard Cite

Measurement results, sediment transport and pollutant dispersion in confluence regions are highly affected by flow structures of open channel junction and it is necessary to find an efficient method that can fully describe the velocity fields in junctions. In this study the velocity field in an open channel junction was investigated by using Artificial Neural Network (ANN) and three dimensional modelling. First, a modified Genetic Algorithm (GA) was introduced, then, an ANN model was optimized and the flow velocity was predicted in a 90 degree channel junction. Also, for three dimensional simulation of the free surface flow in the considered junction ANSYS-CFX software was used. Comparison of the results obtained from ANN and CFX models with laboratory data with root mean square error of 0.094 and 0.182 and percent standard error of prediction of − 9.75 and − 25.71 respectively, showed that the introduced ANN perform better than CFX in modelling velocity field in open channel junction and it was able to predict accurate in different areas and flow-rates.

show abstract

“…Kumar et al (2011) also applied an ANN to obtain ET 0 , while Valdés et al (2003) used another FIS for the interpolation of solar radiation, as this is one of the inputs needed to the PenmanMonteith ET 0 equation (Allen et al, 1998). Pulido-Calvo and Gutiérrez-Estrada (2009) proposed an FIS tuned by a genetic algorithm for irrigation water demand forecasting. Capraro et al (2008) applied a neural approach to infer the water demand and time needed to take the soil moisture level to a desired value.…”

Section: Introductionmentioning

confidence: 99%