Improved higher lead time river flow forecasts using sequential neural network with error updating

[img]
Preview
PDF
Language: English
782Kb
Title:Improved higher lead time river flow forecasts using sequential neural network with error updating
Creators:
Prakash, Om; omprakashiitm at gmail dot com; Former Research Scholar, Department of Civil Engineering, Indian Institute of Technology Madras, Chennai – 600036, India.
Sudheer, K.P.; sudheer at iitm dot ac dot in; Professor, Department of Civil Engineering, Indian Institute of Technology Madras, Chennai – 600036, India.
Srinivasan, K.; ksrini at iitm dot ac dot in; Professor, Department of Civil Engineering, Indian Institute of Technology Madras, Chennai – 600036, India.
Journal or Publication Title:
Journal of Hydrology and Hydromechanics, 62, 1, pp. 60-74
Uncontrolled Keywords:river flow forecasting, forecast lead time, error updating, artificial neural network, genetic algorithm

Abstract

This paper presents a novel framework to use artificial neural network (ANN) for accurate forecasting of river flows at higher lead times. The proposed model, termed as sequential ANN (SANN), is based on the heuristic that a mechanism that provides an accurate representation of physical condition of the basin at the time of forecast, in terms of input information to ANNs at higher lead time, helps improve the forecast accuracy. In SANN, a series of ANNs are connected sequentially to extend the lead time of forecast, each of them taking a forecast value from an immediate pre-ceding network as input. The output of each network is modified by adding an expected value of error so that the residual variance of the forecast series is minimized. The applicability of SANN in hydrological forecasting is illustrated through three case examples: a hypothetical time series, daily river flow forecasting of Kentucky River, USA and hourly river flow forecasting of Kolar River, India. The results demonstrate that SANN is capable of providing accurate forecasts up to 8 steps ahead. A very close fit (>94% efficiency) was obtained between computed and observed flows up to 1 hour in advance for all the cases, and the deterioration in fit was not significant as the forecast lead time increased (92% at 8 steps ahead). The results show that SANN performs much better than traditional ANN models in extending the forecast lead time, suggesting that it can be effectively employed in developing flood management measures.

Official URL: http://147.213.145.2/vc/vc1.asp

Title:Improved higher lead time river flow forecasts using sequential neural network with error updating
Translated title:Improved higher lead time river flow forecasts using sequential neural network with error updating
Creators:
Prakash, Om; omprakashiitm at gmail dot com; Former Research Scholar, Department of Civil Engineering, Indian Institute of Technology Madras, Chennai – 600036, India.
Sudheer, K.P.; sudheer at iitm dot ac dot in; Professor, Department of Civil Engineering, Indian Institute of Technology Madras, Chennai – 600036, India.
Srinivasan, K.; ksrini at iitm dot ac dot in; Professor, Department of Civil Engineering, Indian Institute of Technology Madras, Chennai – 600036, India.
Uncontrolled Keywords:river flow forecasting, forecast lead time, error updating, artificial neural network, genetic algorithm
Subjects:T Technology > TA Engineering (General). Civil engineering (General)
Divisions:Mathematics, Physics and Earth Sciences > Institute of Hydrodynamics > Journal of Hydrology and Hydromechanics
Journal or Publication Title:Journal of Hydrology and Hydromechanics
Volume:62
Number:1
Page Range:pp. 60-74
ISSN:0042-790X
Publisher:Institute of Hydrology of the Slovak Academy of Sciences and the Institute of Hydrodynamics of the Academy of Sciences of the Czech Republic
Related URLs:
URLURL Type
http://avi.lib.cas.cz/node/55Publisher
ID Code:8187
Item Type:Article
Deposited On:05 Jun 2014 18:30
Last Modified:05 Jun 2014 16:30

Citation

Prakash, Om; Sudheer, K.P.; Srinivasan, K. (2014) Improved higher lead time river flow forecasts using sequential neural network with error updating. Journal of Hydrology and Hydromechanics, 62 (1). pp. 60-74. ISSN 0042-790X

Repository Staff Only: item control page