A framework development for predicting the longitudinal dispersion coefficient in natural streams using an artificial neural network

Noori, Roohollah; Karbassi, Abdolreza; Mehdizadeh, Hamid; Naseh, Mohammad Reza Vesali; Sabahi, Mohammad Salman

doi:10.1002/ep.10478

Cited by 71 publications

(24 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This procedure must be repeated many times before the network begins to model the relationship. Details for mastering the art of NN model are published elsewhere [28][29][30][31][32][33].…”

Section: Neural Networkmentioning

confidence: 99%

Development and application of reduced‐order neural network model based on proper orthogonal decomposition for BOD5 monitoring: Active and online prediction

Noori

Karbassi

Ashrafi

et al. 2011

Env Prog and Sustain Energy

Self Cite

View full text Add to dashboard Cite

This study aims at providing a reduced‐order neural network model (RONNM) based on proper orthogonal decomposition (POD) for online prediction of the 5 days biochemical oxygen demand (BOD5). To achieve this goal, the POD method is used to reduce the input vectors to neural network (NN) model. Evaluation of the selected RONNM and its comparison with the model fed with all input vectors (NN model) shows that it reduces not only the output error but also computational cost. Results depict that Pearson correlation coefficient (R) and root mean square error for the best fitted RONNM are 0.94 and 7.75, respectively. Furthermore, accuracy analysis of the output results of models based on developed discrepancy ratio statistic reveals that RONNM is superior. Thus, developed methodology can be considered as an effective tool to train the water resources managers for online evaluation of water quality related to BOD5. © 2011 American Institute of Chemical Engineers Environ Prog, 32: 120–127, 2013.

show abstract

“…This procedure must be repeated many times before the network begins to model the relationship. Details for mastering the art of NN model are published elsewhere [28][29][30][31][32][33].…”

Section: Neural Networkmentioning

confidence: 99%

Development and application of reduced‐order neural network model based on proper orthogonal decomposition for BOD5 monitoring: Active and online prediction

Noori

Karbassi

Ashrafi

et al. 2011

Env Prog and Sustain Energy

Self Cite

View full text Add to dashboard Cite

show abstract

“…As is presented in Eq.-1, D is needed to be determined before model being run. There are plenty available formulas to determine this coeff icient however not all of them have appropriate performance (Noori 2009;Noori 2011). Due to some newly published studies in the related literature, authors came to the conclusion to choose D that is suggested by Zeng & Huai (2014)in this study (Eq.-2).…”

Section: Methodsand Materialsmentioning

confidence: 99%

One-dimensional Transport Simulation of Pollutants in Natural Streams

Ramezani

Karami

Sarang³

2016

AMBIENT SCIENCE

View full text Add to dashboard Cite

Rivers are the main sources of freshwater systems which governments need to manage and plan to maintain them as per an acceptable quality. In this research, a numerical scheme was used and implemented in MATLAB to provide a one-dimensional water quality tool. This code then was tested with two datasets of Chattahoochee and Mackinaw rivers. To evaluate the model performance, results and sampled data were checked in terms of conformity by using three metrics: CE, MARE, and RMSE. Results were almost near to observed data and metrics' values were found satisfactory, showing that the employed numerical approach is an appropriate method for surface water quality planning and management. AbstractIntroduction:

show abstract

“…In order to tackle these issues in intrusive ROMs, a number of non-intrusive reduced order models (NIROMs) have been developed recently [50,53,35,34]. However, very little work can be found addressing non-intrusive model reduction for parameterized PDEs, where inputs (e.g.…”

Section: Introductionmentioning

confidence: 99%

A parameterized non-intrusive reduced order model and error analysis for general time-dependent nonlinear partial differential equations and its applications

Xiao¹,

Fang²,

Pain³

et al. 2017

Computer Methods in Applied Mechanics and Engineering

View full text Add to dashboard Cite

A novel parameterized non-intrusive reduced order model (P-NIROM) based on proper orthogonal decomposition (POD) has been developed. This P-NIROM is a generic and efficient approach for model reduction of parameterized partial differential equations (P-PDEs). Over existing parameterized reduced order models (P-ROM) (most of them are based on the reduced basis method), it is non-intrusive and independent on partial differential equations and computational codes. During the training process, the Smolyak sparse grid method is used to select a set of parameters over a specific parameterized space (Ω p ∈ R P ). For each selected parameter, the reduced basis functions are generated from the snapshots derived from a run of the high fidelity model. More generally, the snapshots and basis function sets for any parameters over Ω p can be obtained using an interpolation method. The P-NIROM can then be constructed by using our recently developed technique [50,53] where either the Smolyak or radial basis function (RBF) methods are used to generate a set of hyper-surfaces representing the underlying dynamical system over the reduced space.The new P-NIROM technique has been applied to parameterized Navier-Stokes equations and implemented with an unstructured mesh finite element model. The capability of this P-NIROM has been illustrated numerically by two test cases: flow past a cylinder and lock exchange case. The prediction capabilities of the P-NIROM have been evaluated by varying the viscosity, initial and boundary conditions. The results show that this P-NIROM has captured the quasi-totality of the details of the flow with CPU speedup of three orders of magnitude. An error analysis for the P-NIROM has been carried out.

show abstract

A framework development for predicting the longitudinal dispersion coefficient in natural streams using an artificial neural network

Cited by 71 publications

References 39 publications

Development and application of reduced‐order neural network model based on proper orthogonal decomposition for BOD5 monitoring: Active and online prediction

Development and application of reduced‐order neural network model based on proper orthogonal decomposition for BOD5 monitoring: Active and online prediction

One-dimensional Transport Simulation of Pollutants in Natural Streams

A parameterized non-intrusive reduced order model and error analysis for general time-dependent nonlinear partial differential equations and its applications

Contact Info

Product

Resources

About