Please use this identifier to cite or link to this item: http://krishikosh.egranth.ac.in/handle/1/5810059999
Authors: Ritun Kumar
Advisor: Kashyap, P.S.
Title: Daily suspended sediment modelling using artificial neural network and co-active neuro fuzzy inference system
Publisher: G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand)
Language: en
Type: Thesis
Pages: 141
Agrotags: null
Keywords: neural networks, sediments, fuzzy logic
Abstract: Sedimentation is the process in which soil substance carried from its point of origin by either natural or human-activities processes is deposited elsewhere on land surfaces or in water bodies. Sediment is a natural product of stream erosion. The sediment load may be increased by human practices. Erosive processes can reduce farm income by decreasing crop yields and increasing maintenance costs for drainage systems. Additional damages in both rural and urban areas are deteriorated water quality, and increased costs of removing sediment from roadways, roadside and surface-water supplies. In the present study an attempt has been made to develop artificial neural network (ANN) based models for estimation of daily suspended sediment during monsoon season at Mancherial, Telangana, India. The daily runoff-sediment data of years 1991-1997 was used to train the models and data of years 19982000 to test the models. The ANN and CANFIS were used for developing of models based on activation functions TanhAxon and Sigmoid Axon and learning rules were Momentum, Quick Prop, Levenberg Marquardt, conjugate Gradient and Delta Bar Delta. Gaussian membership function was used in CANFIS. The performance of the models were evaluated qualitatively by graphical observation and quantitatively using different statistical and hydrological indices viz. root mean square error (RMSE), Nash Sutcliffe efficiency (NSE) and correlation coefficient (r). The results indicate that the ANN models performed better than the CANFIS models. It was concluded that the ANN model can be successfully employed for estimation of daily suspended sediment concentration in the monsoon season at Mancherial, Telangana.
Subject: Agricultural Engineering
Theme: Soil and Water Conservation
Research Problem: Neural Networks
These Type: M.Tech.
Issue Date: 2016-07
Appears in Collections:Theses

Files in This Item:
File Description SizeFormat 
RitunKumar.pdf3.21 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.