Comparative analysis of artificial intelligence techniques for the prediction of infiltration process

Singh, Balraj; Sihag, Parveen; Parsaie, Abbas; Angelaki, Anastasia

doi:10.1080/24749508.2020.1833641

Cited by 36 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researchers describe the ability of perceptron neural networks to detect the relationships between parameters as a unique feature. Most studies have used soft computing modeling in water engineering with multilayer perceptron networks (Singh et al 2021). These networks are primarily trained using backpropagation technique.…”

Section: Multilayer Perceptron Neural Networkmentioning

confidence: 99%

Estimation of Manning Roughness Coefficient in Alluvial Rivers with Bed Forms Using Soft Computing Models

Yarahmadi

Parsaie

Shafai-Bejestan

et al. 2023

Water Resour Manage

Self Cite

View full text Add to dashboard Cite

The bed surface of alluvial rivers is rarely plane and takes different geometric configurations called bed forms. Bed forms are created by the movement of riverbed sediments, especially during floods. The interaction between the flow and bed form is very complex. The flow intensity controls bed forms, and the bed form significantly affects the properties of the flow (such as depth, velocity, and flow resistance). The Manning roughness coefficient is one of the most important flow resistance coefficients, which significantly affects the bed form shape and geometry. This study aimed to estimate the Manning roughness coefficient in rivers with bed forms, using soft computing models, including multilayer perceptron artificial neural network 2 (MLPNN), group method of data handling (GMDH), support vector machine (SVM) model, and genetic programming model (GP). To this end, the energy grade line (𝑆 𝑓 ), flow Froude number (Fr), 𝑦 𝑑 50 ⁄ , ∆ 𝑑 50 ⁄ , ∆ 𝜆 ⁄ , and ∆ 𝑦 ⁄ were used as the input variables, and the Manning roughness coefficient was used as the output variable. The results showed that all the test models have acceptable accuracy, while the SVM model showed the highest level of accuracy with the coefficient of determination 𝑅 2 = 0.99 in the verification stage. The sensitivity analysis of SVM and MLPNN models and the structural analysis of GMDH and GP models indicated that the most important parameters affecting the Manning roughness coefficient areFr, 𝑆 𝑓 , ∆ 𝜆 ⁄ .

show abstract

Section: Multilayer Perceptron Neural Networkmentioning

confidence: 99%

Estimation of Manning Roughness Coefficient in Alluvial Rivers with Bed Forms Using Soft Computing Models

Yarahmadi

Parsaie

Shafai-Bejestan

et al. 2023

Water Resour Manage

Self Cite

View full text Add to dashboard Cite

show abstract

“…ANN is used to model the R-R relationship (Young and Liu, 2015;Vyas et al 2016;Kumar et al 2016;Dounia et al, 2016;Asadi et al 2019), to predict rainfall (Lee et al, 1998;Mirabbasi et al 2019), to predict river flow (Guimaraes Santos and Silva, 2014;Shi et al, 2016;Zemzami and Benaabidate, 2016;Wagena et al 2020;Adnan et al 2021), to predict reference evapotranspiration (Aytek, 2008;Qasem et al 2019;Tikhamarine et al 2019;Elbeltagi et al 2022), to predict discharge and waterlevel (Khan et al, 2016;Nacar et al 2018;Anilan et al 2020;Damla et al 2020;Temiz et al 2021), to predict snowmelt-runoff (Yilmaz, 2011), ANNs have also been regarded as a powerful tool for use in a variety of underground water problems (Malik et al 2021;Wunsch et al 2021). ANNs can be used for other purposes is unit hydrograph derivation (Lange, 1998), flood frequency analysis (Campolo, 2003;Dawson, et al, 2006;, drought analysis (Shin and Salas, 2000;Ochoa-Rivera, 2008;Banadkooki et al 2021;Ozan Evkaya and Sevinç Kurnaz, 2021), suspended sediment data estimation (Jimeno-Sáez, 2018;Khan et al 2019;Meshram et al 2020), Modelling the infiltration process Sihag et al 2021;Singh et al 2021), estimation of hydroelectric generation (Uzlu et al, 2014;Niu et...…”

Section: Literature Surveymentioning

confidence: 99%

Monthly Stream Flows Estimation in the Karasu River of Euphrates Basin With Artificial Neural Networks Approach

Katipoğlu

2022

Mühendislik Bilimleri Ve Tasarım Dergisi

View full text Add to dashboard Cite

This study aims to estimate streamflow values with artificial neural networks (ANN) using various meteorological parameters. In developing the ANN model, various combinations of precipitation, air temperatures, and potential evapotranspiration values were used as inputs, and streamflow values were obtained. Meteorological data is divided into 70% train, 15% test, and 15% validation. In the model's design, various training algorithms, network architecture, input combinations, and the number of iterations were tried, and the most suitable model was tested. Correlation coefficient (R), coefficient of determination (R2), absolute error (AE), and absolute relative error (ARE) coefficients were compared, and the most suitable model was selected. According to the analysis results, the optimal model was obtained using 2000 iterations, the architecture of the 4-4-1 model, and the Quasi-Newton algorithm. It was determined that the ANNs successfully modeled the rainfall-runoff relationship and produced reliable estimates. In addition, it was revealed that the inclusion of potential evapotranspiration values obtained by the Thornthwaite method into the model increases the model's success.

show abstract

“…Climate change reacts on precipitation, affecting evapotranspiration, runoff and infiltration rates. Designing an irrigation network is directly related to infiltration, because of the impact on the hydraulic parameters [7,8]. Field capacity is linked to soil moisture; it depends on the soil texture/structure [9].…”

Section: Introductionmentioning

confidence: 99%

Assessment of Contamination Management Caused by Copper and Zinc Cations Leaching and Their Impact on the Hydraulic Properties of a Sandy and a Loamy Clay Soil

Angelaki

Dionysidis

Sihag

et al. 2022

Land

Self Cite

View full text Add to dashboard Cite

Soil hydraulic properties are crucial to agriculture and water management and depend on soil structure. The impact of Cu and Zn cations on the hydraulic properties of sandy and loamy clay soil samples of Central Greece, was investigated in the present study. Metal solutions with increased concentrations were used to contaminate the soil samples and the effect on hydraulic properties was evaluated, demonstrating the innovation of the current study. The soil samples were packed separately into transparent columns and the initial values of hydraulic conductivity, cumulative infiltration, infiltration rate and sorptivity were estimated. In order to evaluate soil adsorption, metal concentrations were measured at the water leachate. After the contamination of the soil samples, the hydraulic properties under investigation were determined again, using distilled water as the incoming fluid; the differences at the hydraulic parameters were observed. After doubling metal concentrations into the incoming solution of loamy clay soil, metal adsorption and the values of the hydraulic parameters increased significantly. Loamy clay soil showed interaction between the clay particles and the positive charge in the incoming fluid, which led to a possible increase in aggregation. Furthermore, aggregation may led to pore generation. Contamination of sandy soil exhibited no impact on aggregation and soil structure. In order to evaluate the differences on the hydraulic properties and soil structure, the experimental points were approximated with two infiltration models.

show abstract

Comparative analysis of artificial intelligence techniques for the prediction of infiltration process

Cited by 36 publications

References 24 publications

Estimation of Manning Roughness Coefficient in Alluvial Rivers with Bed Forms Using Soft Computing Models

Estimation of Manning Roughness Coefficient in Alluvial Rivers with Bed Forms Using Soft Computing Models

Monthly Stream Flows Estimation in the Karasu River of Euphrates Basin With Artificial Neural Networks Approach

Assessment of Contamination Management Caused by Copper and Zinc Cations Leaching and Their Impact on the Hydraulic Properties of a Sandy and a Loamy Clay Soil

Contact Info

Product

Resources

About