Use of Data Driven Techniques for Short Lead Time Streamflow Forecasting in Mahanadi basin

Pandey, Alok and Srinivas, VV (2015) Use of Data Driven Techniques for Short Lead Time Streamflow Forecasting in Mahanadi basin. In: INTERNATIONAL CONFERENCE ON WATER RESOURCES, COASTAL AND OCEAN ENGINEERING (ICWRCOE'15) , MAR 11-14, 2015, Natl Inst Technol Karnataka, Mangaluru, INDIA, pp. 972-978.

PDF Aqu_Pro_4-972-2015.pdf - Published Version Restricted to Registered users only Download (274kB) | Request a copy

Abstract

Streamflow forecasts at daily time scale are necessary for effective management of water resources systems. Typical applications include flood control, water quality management, water supply to multiple stakeholders, hydropower and irrigation systems. Conventionally physically based conceptual models and data-driven models are used for forecasting streamflows. Conceptual models require detailed understanding of physical processes governing the system being modeled. Major constraints in developing effective conceptual models are sparse hydrometric gauge network and short historical records that limit our understanding of physical processes. On the other hand, data-driven models rely solely on previous hydrological and meteorological data without directly taking into account the underlying physical processes. Among various data driven models Auto Regressive Integrated Moving Average (ARIMA), Artificial Neural Networks (ANNs) are most widely used techniques. The present study assesses performance of ARIMA and ANNs methods in arriving at one-to seven-day ahead forecast of daily streamflows at Basantpur streamgauge site that is situated at upstream of Hirakud Dam in Mahanadi river basin, India. The ANNs considered include Feed-Forward back propagation Neural Network (FFNN) and Radial Basis Neural Network (RBNN). Daily streamflow forecasts at Basantpur site find use in management of water from Hirakud reservoir. (C) 2015 The Authors. Published by Elsevier B.V.

Item Type:	Conference Proceedings
Series.:	Aquatic Procedia
Publisher:	ELSEVIER SCIENCE BV
Additional Information:	Copy right for this article belongs to the ELSEVIER SCIENCE BV, SARA BURGERHARTSTRAAT 25, PO BOX 211, 1000 AE AMSTERDAM, NETHERLANDS
Keywords:	Forecasting; Streamflow; Data Driven Methods; ANN; ARMA
Department/Centre:	Division of Mechanical Sciences > Civil Engineering
Date Deposited:	15 Jun 2015 09:25
Last Modified:	15 Jun 2015 09:25
URI:	http://eprints.iisc.ac.in/id/eprint/51666

Actions (login required)

View Item