Wavelets-based non-linear model for real-time daily flow forecasting in Krishna River

Maheswaran Rathinasamy, Rakesh Khosa

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

In this study, a multi-scale non-linear model based on coupling a discrete wavelet transform (DWT) and the second-order Volterra model, i.e. the wavelet Volterra coupled (WVC) model, is applied for daily inflow forecasting at Krishna Agraharam, Krishna River, India. The relative performance of the WVC model was compared with regular artificial neural networks (ANN), wavelet-artificial neural networks (WA-ANN) models and other baseline models such as auto-regressive moving average with exogenous variables (ARMAX) for lead times of 1-5 days. The models were applied for the forecasting of daily streamflow at Krishna Agraharam Station at Krishna River. The WVC performed very well, especially when compared with the WA-ANN model for lead times of 4 and 5 days. The results indicate that the WVC model is a promising alternative to the other traditional models for short-term flow forecasting.

Original languageEnglish (US)
Pages (from-to)1022-1041
Number of pages20
JournalJournal of Hydroinformatics
Volume15
Issue number3
DOIs
StatePublished - Jan 1 2013

Fingerprint

wavelet
Rivers
river
artificial neural network
Neural networks
Discrete wavelet transforms
streamflow
inflow
transform

Keywords

  • Krishna river basin
  • Rainfall-runoff modelling
  • Real-time flood forecasting
  • Volterra model
  • Wavelet-based models

Cite this

Wavelets-based non-linear model for real-time daily flow forecasting in Krishna River. / Rathinasamy, Maheswaran; Khosa, Rakesh.

In: Journal of Hydroinformatics, Vol. 15, No. 3, 01.01.2013, p. 1022-1041.

Research output: Contribution to journalArticle

Rathinasamy, Maheswaran ; Khosa, Rakesh. / Wavelets-based non-linear model for real-time daily flow forecasting in Krishna River. In: Journal of Hydroinformatics. 2013 ; Vol. 15, No. 3. pp. 1022-1041.
@article{7b0b7c66d3384eb0ac63691cccae6376,
title = "Wavelets-based non-linear model for real-time daily flow forecasting in Krishna River",
abstract = "In this study, a multi-scale non-linear model based on coupling a discrete wavelet transform (DWT) and the second-order Volterra model, i.e. the wavelet Volterra coupled (WVC) model, is applied for daily inflow forecasting at Krishna Agraharam, Krishna River, India. The relative performance of the WVC model was compared with regular artificial neural networks (ANN), wavelet-artificial neural networks (WA-ANN) models and other baseline models such as auto-regressive moving average with exogenous variables (ARMAX) for lead times of 1-5 days. The models were applied for the forecasting of daily streamflow at Krishna Agraharam Station at Krishna River. The WVC performed very well, especially when compared with the WA-ANN model for lead times of 4 and 5 days. The results indicate that the WVC model is a promising alternative to the other traditional models for short-term flow forecasting.",
keywords = "Krishna river basin, Rainfall-runoff modelling, Real-time flood forecasting, Volterra model, Wavelet-based models",
author = "Maheswaran Rathinasamy and Rakesh Khosa",
year = "2013",
month = "1",
day = "1",
doi = "10.2166/hydro.2013.135",
language = "English (US)",
volume = "15",
pages = "1022--1041",
journal = "Journal of Hydroinformatics",
issn = "1464-7141",
publisher = "IWA Publishing",
number = "3",

}

TY - JOUR

T1 - Wavelets-based non-linear model for real-time daily flow forecasting in Krishna River

AU - Rathinasamy, Maheswaran

AU - Khosa, Rakesh

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In this study, a multi-scale non-linear model based on coupling a discrete wavelet transform (DWT) and the second-order Volterra model, i.e. the wavelet Volterra coupled (WVC) model, is applied for daily inflow forecasting at Krishna Agraharam, Krishna River, India. The relative performance of the WVC model was compared with regular artificial neural networks (ANN), wavelet-artificial neural networks (WA-ANN) models and other baseline models such as auto-regressive moving average with exogenous variables (ARMAX) for lead times of 1-5 days. The models were applied for the forecasting of daily streamflow at Krishna Agraharam Station at Krishna River. The WVC performed very well, especially when compared with the WA-ANN model for lead times of 4 and 5 days. The results indicate that the WVC model is a promising alternative to the other traditional models for short-term flow forecasting.

AB - In this study, a multi-scale non-linear model based on coupling a discrete wavelet transform (DWT) and the second-order Volterra model, i.e. the wavelet Volterra coupled (WVC) model, is applied for daily inflow forecasting at Krishna Agraharam, Krishna River, India. The relative performance of the WVC model was compared with regular artificial neural networks (ANN), wavelet-artificial neural networks (WA-ANN) models and other baseline models such as auto-regressive moving average with exogenous variables (ARMAX) for lead times of 1-5 days. The models were applied for the forecasting of daily streamflow at Krishna Agraharam Station at Krishna River. The WVC performed very well, especially when compared with the WA-ANN model for lead times of 4 and 5 days. The results indicate that the WVC model is a promising alternative to the other traditional models for short-term flow forecasting.

KW - Krishna river basin

KW - Rainfall-runoff modelling

KW - Real-time flood forecasting

KW - Volterra model

KW - Wavelet-based models

UR - http://www.scopus.com/inward/record.url?scp=84883577990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883577990&partnerID=8YFLogxK

U2 - 10.2166/hydro.2013.135

DO - 10.2166/hydro.2013.135

M3 - Article

VL - 15

SP - 1022

EP - 1041

JO - Journal of Hydroinformatics

JF - Journal of Hydroinformatics

SN - 1464-7141

IS - 3

ER -