Constructing prediction interval for artificial neural network rainfall runoff models based on ensemble simulations

K. S. Kasiviswanathan, Fnu Cibin Raj, K. P. Sudheer, I. Chaubey

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

This paper presents a method of constructing prediction interval for artificial neural network (ANN) rainfall runoff models during calibration with a consideration of generating ensemble predictions. A two stage optimization procedure is envisaged in this study for construction of prediction interval for the ANN output. In Stage 1, ANN model is trained with genetic algorithm (GA) to obtain optimal set of weights and biases vector. In Stage 2, possible variability of ANN parameters (obtained in Stage 1) is optimized so as to create an ensemble of models with the consideration of minimum residual variance for the ensemble mean, while ensuring a maximum of the measured data to fall within the estimated prediction interval. The width of the prediction interval is also minimized simultaneously. The method is demonstrated using a real world case study of rainfall runoff data for an Indian basin. The method was able to produce ensembles with a prediction interval (average width) of 26.49m3/s with 97.17% of the total observed data points lying within the interval in validation. One specific advantage of the method is that when ensemble mean value is considered as a forecast, the peak flows are predicted with improved accuracy by this method compared to traditional single point forecasted ANNs.

Original languageEnglish (US)
Pages (from-to)275-288
Number of pages14
JournalJournal of Hydrology
Volume499
DOIs
StatePublished - Aug 13 2013

Fingerprint

artificial neural network
runoff
rainfall
prediction
simulation
peak flow
genetic algorithm
method
calibration
basin

All Science Journal Classification (ASJC) codes

  • Water Science and Technology

Cite this

@article{e65a825583af4f66bfeb123a640187d6,
title = "Constructing prediction interval for artificial neural network rainfall runoff models based on ensemble simulations",
abstract = "This paper presents a method of constructing prediction interval for artificial neural network (ANN) rainfall runoff models during calibration with a consideration of generating ensemble predictions. A two stage optimization procedure is envisaged in this study for construction of prediction interval for the ANN output. In Stage 1, ANN model is trained with genetic algorithm (GA) to obtain optimal set of weights and biases vector. In Stage 2, possible variability of ANN parameters (obtained in Stage 1) is optimized so as to create an ensemble of models with the consideration of minimum residual variance for the ensemble mean, while ensuring a maximum of the measured data to fall within the estimated prediction interval. The width of the prediction interval is also minimized simultaneously. The method is demonstrated using a real world case study of rainfall runoff data for an Indian basin. The method was able to produce ensembles with a prediction interval (average width) of 26.49m3/s with 97.17{\%} of the total observed data points lying within the interval in validation. One specific advantage of the method is that when ensemble mean value is considered as a forecast, the peak flows are predicted with improved accuracy by this method compared to traditional single point forecasted ANNs.",
author = "Kasiviswanathan, {K. S.} and {Cibin Raj}, Fnu and Sudheer, {K. P.} and I. Chaubey",
year = "2013",
month = "8",
day = "13",
doi = "10.1016/j.jhydrol.2013.06.043",
language = "English (US)",
volume = "499",
pages = "275--288",
journal = "Journal of Hydrology",
issn = "0022-1694",
publisher = "Elsevier",

}

Constructing prediction interval for artificial neural network rainfall runoff models based on ensemble simulations. / Kasiviswanathan, K. S.; Cibin Raj, Fnu; Sudheer, K. P.; Chaubey, I.

In: Journal of Hydrology, Vol. 499, 13.08.2013, p. 275-288.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Constructing prediction interval for artificial neural network rainfall runoff models based on ensemble simulations

AU - Kasiviswanathan, K. S.

AU - Cibin Raj, Fnu

AU - Sudheer, K. P.

AU - Chaubey, I.

PY - 2013/8/13

Y1 - 2013/8/13

N2 - This paper presents a method of constructing prediction interval for artificial neural network (ANN) rainfall runoff models during calibration with a consideration of generating ensemble predictions. A two stage optimization procedure is envisaged in this study for construction of prediction interval for the ANN output. In Stage 1, ANN model is trained with genetic algorithm (GA) to obtain optimal set of weights and biases vector. In Stage 2, possible variability of ANN parameters (obtained in Stage 1) is optimized so as to create an ensemble of models with the consideration of minimum residual variance for the ensemble mean, while ensuring a maximum of the measured data to fall within the estimated prediction interval. The width of the prediction interval is also minimized simultaneously. The method is demonstrated using a real world case study of rainfall runoff data for an Indian basin. The method was able to produce ensembles with a prediction interval (average width) of 26.49m3/s with 97.17% of the total observed data points lying within the interval in validation. One specific advantage of the method is that when ensemble mean value is considered as a forecast, the peak flows are predicted with improved accuracy by this method compared to traditional single point forecasted ANNs.

AB - This paper presents a method of constructing prediction interval for artificial neural network (ANN) rainfall runoff models during calibration with a consideration of generating ensemble predictions. A two stage optimization procedure is envisaged in this study for construction of prediction interval for the ANN output. In Stage 1, ANN model is trained with genetic algorithm (GA) to obtain optimal set of weights and biases vector. In Stage 2, possible variability of ANN parameters (obtained in Stage 1) is optimized so as to create an ensemble of models with the consideration of minimum residual variance for the ensemble mean, while ensuring a maximum of the measured data to fall within the estimated prediction interval. The width of the prediction interval is also minimized simultaneously. The method is demonstrated using a real world case study of rainfall runoff data for an Indian basin. The method was able to produce ensembles with a prediction interval (average width) of 26.49m3/s with 97.17% of the total observed data points lying within the interval in validation. One specific advantage of the method is that when ensemble mean value is considered as a forecast, the peak flows are predicted with improved accuracy by this method compared to traditional single point forecasted ANNs.

UR - http://www.scopus.com/inward/record.url?scp=84881236620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881236620&partnerID=8YFLogxK

U2 - 10.1016/j.jhydrol.2013.06.043

DO - 10.1016/j.jhydrol.2013.06.043

M3 - Article

AN - SCOPUS:84881236620

VL - 499

SP - 275

EP - 288

JO - Journal of Hydrology

JF - Journal of Hydrology

SN - 0022-1694

ER -