Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/45177
Title: Predicting the rainfall-runoff process through non-linear regression
Authors: Aravinda Uvindu Bandara Karunaratne
Keywords: DRNTU::Engineering::Civil engineering::Water resources
Issue Date: 2011
Abstract: The need for accurate rainfall–runoff models has grown significantly due to the increased importance of hydrology to solve the issues arising from changing land-use and rapid urbanization. However, considering the high stochastic property of the process, many models are still being developed in order to define this complex phenomenon. Recently, Artificial Intelligence (AI) techniques such as the Artificial Neural Network (ANN) and the Adaptive Neural-Fuzzy Inference System (ANFIS) have been extensively used by hydrologists for rainfall–runoff modelling. Continuing investigations on the application of hydrologic accounting to runoff prediction have been directed largely towards the development of improved models for the determining of runoff. The existing rainfall-runoff prediction models necessarily have complications such as the use of many variables in obtaining the dependent variable. This study has built a model to predict the runoff using rainfall data by means of non-linear (quadratic) regression. In order to compare the efficiency of the non-linear (quadratic) regression model, the study has carried out a parallel comparative model built by means of multiple-linear regression. The model proposed by this study suggests a researcher-friendly approach with the use of minimum number of variables to obtaining a relationship between the rainfall and the runoff.
URI: http://hdl.handle.net/10356/45177
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:CEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
cWR19-2011.pdf
  Restricted Access
1.44 MBAdobe PDFView/Open

Page view(s)

314
Updated on Nov 23, 2020

Download(s)

24
Updated on Nov 23, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.