Predicting longitudinal dispersion coefficient using ANN with metaheuristic training algorithms

Alizadeh, Mohamad Javad; Shabani, Amir; Kavianpour, Mohammad Reza

doi:10.1007/s13762-017-1307-1

Cited by 30 publications

(15 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For complex case studies such as the natural rivers with large transverse velocity shear, the dispersion coefficient estimation is time-consuming with a high level of uncertainties [10,16]. According to the previous studies, the flow depth (H), section width (B), mean flow velocity (U), bed shear velocity (U*), river shape parameter (b), channel sinuosity (s) in river sections and the combinations of them (e.g., the flow discharge, Q) are the most influential parameters for determination of the Kx [17,18,19,20,21]. Based on these hydraulic and hydrodynamic parameters, several researches were carried out to develop a formula for estimation of the Kx based on the following representation For this purpose, several methods including empirical/mathematical based equations [22,23,24,25], statistical and regression-based equations [14,17,26,27] and in recent years different models of soft computing such as adaptive neuro fuzzy inference system (ANFIS), support vector machine (SVM), Gene expression programming (GEP) and ANN [3,6,9,11,12,28,29,30,31] were used to predict and develop a formula that can be used in the estimation of Kx in natural rivers.…”

Section: Introductionmentioning

confidence: 99%

“…Soft computing techniques work as a black-box model in which the process of a phenomenon is not considered in modeling, and the governing relationship is just based on the input-output data without providing explicit estimation equation [32,33]. The ANN is the most widely used method in water resources modeling [4,20,34,35,36]. Multilayer perceptron (MLP) with a feed-forward back-propagation algorithm is one of the most popular types of ANN, which was used for forecasting hydrological variables such as drought, streamflow, evaporation, etc [37,38,39,40,41,42].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Derivation of Optimized Equations for Estimation of Dispersion Coefficient in Natural Streams Using Hybridized ANN With PSO and CSO Algorithms

et al. 2020

View full text Add to dashboard Cite

In this paper, a new hybrid model is developed to improve the accuracy in the prediction of the longitudinal dispersion coefficient (Kx) and the derivation of novel optimized explicit equations for natural streams. For this purpose, an artificial neural network (ANN) is hybridized with particle swarm optimization (PSO) and cat swarm optimization (CSO) algorithms. The CSO and PSO are used to find the optimum values of biases and weights in ANN structure and formulate the results as novel explicit predictive equations than the classical black-box methods. The hydraulic parameters of the natural stream and some geometric parameters were utilized for the model developments. Eight different input combinations are used as the input vectors to ANN, ANN-PSO, and ANN-CSO models, whereas the dispersion coefficient (Kx) is the target model output. The developed models are trained and tested bya comprehensive reference data sets measured on streams in the United States, that were used previously by Tayfur and Singh (2005) in ANN models. The main aims, novelty, and contributions of the present study are 1) improving the accuracy of classical ANN-based Kx predictions by hybridizing with CSO and PSO. 2) Performing sensitive analysis of ANN, ANN-CSO, and ANN-PSO based on input combinations 3) derivation of novel explicit optimized ANN-CSO, ANN-PSO, equations for predicting Kx rather than the classical ANN black-box methods. The results depicted that the highest accuracy and superiority were attained by the ANN-PSO model, with input variables of B, H, U, U*, followed by ANN-CSO and ANN. By using the optimized trained black box ANN models, two novel explicit predictive equations are derived, and their results are compared with the empirical equations. Comparative assessments confirmed significant improvements in the hybrid equations' results than the classical ANN and previously published equations. The developed novel equations can be used to estimate the Kx in one-dimensional pollutant transfer models that are essential for the pollution studies in environmental river engineering practices.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Derivation of Optimized Equations for Estimation of Dispersion Coefficient in Natural Streams Using Hybridized ANN With PSO and CSO Algorithms

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The new position of the particle is updated by using Equation 2; here the new position of the particle is denoted by +1 , is the current position, and +1 is the updated velocity of the particle [25][26][27].…”

Section: Methodsmentioning

confidence: 99%

“…Eberhart and Kennedy (1995) first created it. This optimization method is a kind of swarm intelligence inspired by the social behavior and dynamic motion of flocks of birds and fish [25,28]. Basically, the PSO algorithm integrates the particles ' selfexperiences with their social experiences in search of globally optimal a lternatives.…”

Section: Particle Swarm Optimization (Pso)mentioning

confidence: 99%

Time-Cost-Quality Trade-off Model for Optimal Pile Type Selection Using Discrete Particle Swarm Optimization Algorithm

Lateef

Burhan

2019

Civ Eng J

View full text Add to dashboard Cite

The cost of pile foundations is part of the super structure cost, and it became necessary to reduce this cost by studying the pile types then decision-making in the selection of the optimal pile type in terms of cost and time of production and quality .So The main objective of this study is to solve the time–cost–quality trade-off (TCQT) problem by finding an optimal pile type with the target of "minimizing" cost and time while "maximizing" quality. There are many types In the world of piles but in this paper, the researcher proposed five pile types, one of them is not a traditional, and developed a model for the problem and then employed particle swarm optimization (PSO) algorithm, as one of evolutionary algorithms with the help of (Mat lab software), as a tool for decision making problem about choosing the best alternative of the traded piles, and proposes a multi objective optimization model, which aims to optimize the time, cost and quality of the pile types, and assist in selecting the most appropriate pile types. The researcher selected 10 of senior engineers to conduct interviews with them. And prepared some questions for interviews and open questionnaire. The individuals are selected from private and state sectors each one have 10 years or more experience in pile foundations work. From personal interviews and field survey the research has shown that most of the experts, engineers are not fully aware of new soft wear techniques to helps them in choosing alternatives, despite their belief in the usefulness of using modern technology and software. The Problem is multi objective optimization problem, so after running the PSO algorithm it is usual to have more than one optimal solution, for five proposed pile types, finally the researcher evaluated and discussed the output results and found out that pre-high tension spun (PHC)pile type was the optimal pile type.

show abstract

“…bee algorithm, cuckoo, and imperialist competitive algorithms). However, the Levenberg-Marquardt algorithm is among the most common types and fastest techniques for training ANN models (Alizadeh, Shabani, et al, 2017). The SVR model was developed according to its library in MATLAB and the default values were set for the model.…”

Section: Modeling Proceduresmentioning

confidence: 99%

Prediction of significant wave height; comparison between nested grid numerical model, and machine learning models of artificial neural networks, extreme learning and support vector machines

Shamshirband

Mosavi

Rabczuk

et al. 2020

Engineering Applications of Computational Fluid Mechanics

View full text Add to dashboard Cite

show abstract

Predicting longitudinal dispersion coefficient using ANN with metaheuristic training algorithms

Cited by 30 publications

References 37 publications

Derivation of Optimized Equations for Estimation of Dispersion Coefficient in Natural Streams Using Hybridized ANN With PSO and CSO Algorithms

Derivation of Optimized Equations for Estimation of Dispersion Coefficient in Natural Streams Using Hybridized ANN With PSO and CSO Algorithms

Time-Cost-Quality Trade-off Model for Optimal Pile Type Selection Using Discrete Particle Swarm Optimization Algorithm

Prediction of significant wave height; comparison between nested grid numerical model, and machine learning models of artificial neural networks, extreme learning and support vector machines

Contact Info

Product

Resources

About