Follow
International Journal of Current Microbiology and Applied Sciences (IJCMAS)
IJCMAS is now DOI (CrossRef) registered Research Journal. The DOIs are assigned to all published IJCMAS Articles.
Index Copernicus ICI Journals Master List 2018 - IJCMAS--ICV 2018: 95.39 For more details click here
National Academy of Agricultural Sciences (NAAS) : NAAS Score: *5.38 (2020) [Effective from January 1, 2020]For more details click here

Login as a Reviewer

Indexed in



National Academy of Agricultural Sciences (NAAS)
NAAS Score: *5.38 (2020)
[Effective from January 1, 2020]
For more details click here

ICV 2018: 95.39
Index Copernicus ICI Journals Master List 2018 - IJCMAS--ICV 2018: 95.39
For more details click here

See Guidelines to Authors
Current Issues

Original Research Articles

PRINT ISSN : 2319-7692
Online ISSN : 2319-7706
Issues : 12 per year
Publisher : Excellent Publishers
Email : editorijcmas@gmail.com / submit@ijcmas.com
Editor-in-chief: Dr.M.Prakash
Index Copernicus ICV 2018: 95.39
NAAS RATING 2020: 5.38

Int.J.Curr.Microbiol.App.Sci.2017.6(10): 1386-1399
DOI: https://doi.org/10.20546/ijcmas.2017.610.164


Suspended Sediment Modeling with Continuously Lagging Input Variables Using Artificial Intelligence and Physics based Models
Daniel Prakash Kushwaha* and Devendra Kumar
Department of Soil and Water Conservation Engineering, College of Technology, G. B. Pant University of Agriculture and Technology, Pantnagar-263145, Uttarakhand, India
*Corresponding author
Abstract:

Artificial neural network (ANN) models were developed to predict daily suspended sediment concentration (SSC) for the Baitarani River at Champua station using daily SSC and daily discharge. ANN models were calibrated by using multilayer feed forward back propagation neural networks with sigmoid activation function and Levenberg-Marquardt (L-M) learning algorithm. The performance of the developed models was evaluated qualitatively and quantitatively. In qualitative evaluation of models, observed suspended sediment concentration (OSCC) and computed suspended sediment concentration (CSSC) were compared using sediment hydrographs and scatter plots during testing period. Akaike’s information criterion (AIC), correlation coefficient (r), mean square error (MSE), root mean square error (RMSE), minimum description length (MDL), coefficient of efficiency (CE) and normalized mean square error (NMSE) indices were used for quantitative performance evaluation of the models. Results indicate that M-6 model with (7-5-5-1) network architecture is better than all models and it was also found that ANN based model is better than physics based models such as sediment rating curve and multiple linear regression for the prediction of SSC.


Keywords: Sediment rating curve, Multiple linear regression, Artificial neural network, Minimum description length, Akaike’s information criterion.
Download this article as Download

How to cite this article:

Daniel Prakash Kushwaha and Devendra Kumar. 2017. Suspended Sediment Modeling with Continuously Lagging Input Variables Using Artificial Intelligence and Physics based Models.Int.J.Curr.Microbiol.App.Sci. 6(10): 1386-1399. doi: https://doi.org/10.20546/ijcmas.2017.610.164