Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia

A. El-Shafie, A. Noureldin, Mohd. Raihan Taha, Aini Hussain, M. Mukhlisin

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Rainfall is considered as one of the major components of the hydrological process; it takes significant part in evaluating drought and flooding events. Therefore, it is important to have an accurate model for rainfall forecasting. Recently, several data-driven modeling approaches have been investigated to perform such forecasting tasks as multi-layer perceptron neural networks (MLP-NN). In fact, the rainfall time series modeling involves an important temporal dimension. On the other hand, the classical MLP-NN is a static and has a memoryless network architecture that is effective for complex nonlinear static mapping. This research focuses on investigating the potential of introducing a neural network that could address the temporal relationships of the rainfall series. Two different static neural networks and one dynamic neural network, namely the multi-layer perceptron neural network (MLP-NN), radial basis function neural network (RBFNN) and input delay neural network (IDNN), respectively, have been examined in this study. Those models had been developed for the two time horizons for monthly and weekly rainfall forecasting at Klang River, Malaysia. Data collected over 12 yr (1997-2008) on a weekly basis and 22 yr (1987-2008) on a monthly basis were used to develop and examine the performance of the proposed models. Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static and dynamic neural networks. Results showed that the MLP-NN neural network model is able to follow trends of the actual rainfall, however, not very accurately. RBFNN model achieved better accuracy than the MLP-NN model. Moreover, the forecasting accuracy of the IDNN model was better than that of static network during both training and testing stages, which proves a consistent level of accuracy with seen and unseen data.

Original languageEnglish
Pages (from-to)1151-1169
Number of pages19
JournalHydrology and Earth System Sciences
Volume16
Issue number4
DOIs
Publication statusPublished - 2012

Fingerprint

river basin
rainfall
modeling
flooding
drought
time series
river

ASJC Scopus subject areas

  • Earth and Planetary Sciences (miscellaneous)
  • Water Science and Technology

Cite this

Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia. / El-Shafie, A.; Noureldin, A.; Taha, Mohd. Raihan; Hussain, Aini; Mukhlisin, M.

In: Hydrology and Earth System Sciences, Vol. 16, No. 4, 2012, p. 1151-1169.

Research output: Contribution to journalArticle

@article{2e5534cc27f646d29b3306c4ce0edf38,
title = "Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia",
abstract = "Rainfall is considered as one of the major components of the hydrological process; it takes significant part in evaluating drought and flooding events. Therefore, it is important to have an accurate model for rainfall forecasting. Recently, several data-driven modeling approaches have been investigated to perform such forecasting tasks as multi-layer perceptron neural networks (MLP-NN). In fact, the rainfall time series modeling involves an important temporal dimension. On the other hand, the classical MLP-NN is a static and has a memoryless network architecture that is effective for complex nonlinear static mapping. This research focuses on investigating the potential of introducing a neural network that could address the temporal relationships of the rainfall series. Two different static neural networks and one dynamic neural network, namely the multi-layer perceptron neural network (MLP-NN), radial basis function neural network (RBFNN) and input delay neural network (IDNN), respectively, have been examined in this study. Those models had been developed for the two time horizons for monthly and weekly rainfall forecasting at Klang River, Malaysia. Data collected over 12 yr (1997-2008) on a weekly basis and 22 yr (1987-2008) on a monthly basis were used to develop and examine the performance of the proposed models. Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static and dynamic neural networks. Results showed that the MLP-NN neural network model is able to follow trends of the actual rainfall, however, not very accurately. RBFNN model achieved better accuracy than the MLP-NN model. Moreover, the forecasting accuracy of the IDNN model was better than that of static network during both training and testing stages, which proves a consistent level of accuracy with seen and unseen data.",
author = "A. El-Shafie and A. Noureldin and Taha, {Mohd. Raihan} and Aini Hussain and M. Mukhlisin",
year = "2012",
doi = "10.5194/hess-16-1151-2012",
language = "English",
volume = "16",
pages = "1151--1169",
journal = "Hydrology and Earth System Sciences",
issn = "1027-5606",
publisher = "European Geosciences Union",
number = "4",

}

TY - JOUR

T1 - Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia

AU - El-Shafie, A.

AU - Noureldin, A.

AU - Taha, Mohd. Raihan

AU - Hussain, Aini

AU - Mukhlisin, M.

PY - 2012

Y1 - 2012

N2 - Rainfall is considered as one of the major components of the hydrological process; it takes significant part in evaluating drought and flooding events. Therefore, it is important to have an accurate model for rainfall forecasting. Recently, several data-driven modeling approaches have been investigated to perform such forecasting tasks as multi-layer perceptron neural networks (MLP-NN). In fact, the rainfall time series modeling involves an important temporal dimension. On the other hand, the classical MLP-NN is a static and has a memoryless network architecture that is effective for complex nonlinear static mapping. This research focuses on investigating the potential of introducing a neural network that could address the temporal relationships of the rainfall series. Two different static neural networks and one dynamic neural network, namely the multi-layer perceptron neural network (MLP-NN), radial basis function neural network (RBFNN) and input delay neural network (IDNN), respectively, have been examined in this study. Those models had been developed for the two time horizons for monthly and weekly rainfall forecasting at Klang River, Malaysia. Data collected over 12 yr (1997-2008) on a weekly basis and 22 yr (1987-2008) on a monthly basis were used to develop and examine the performance of the proposed models. Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static and dynamic neural networks. Results showed that the MLP-NN neural network model is able to follow trends of the actual rainfall, however, not very accurately. RBFNN model achieved better accuracy than the MLP-NN model. Moreover, the forecasting accuracy of the IDNN model was better than that of static network during both training and testing stages, which proves a consistent level of accuracy with seen and unseen data.

AB - Rainfall is considered as one of the major components of the hydrological process; it takes significant part in evaluating drought and flooding events. Therefore, it is important to have an accurate model for rainfall forecasting. Recently, several data-driven modeling approaches have been investigated to perform such forecasting tasks as multi-layer perceptron neural networks (MLP-NN). In fact, the rainfall time series modeling involves an important temporal dimension. On the other hand, the classical MLP-NN is a static and has a memoryless network architecture that is effective for complex nonlinear static mapping. This research focuses on investigating the potential of introducing a neural network that could address the temporal relationships of the rainfall series. Two different static neural networks and one dynamic neural network, namely the multi-layer perceptron neural network (MLP-NN), radial basis function neural network (RBFNN) and input delay neural network (IDNN), respectively, have been examined in this study. Those models had been developed for the two time horizons for monthly and weekly rainfall forecasting at Klang River, Malaysia. Data collected over 12 yr (1997-2008) on a weekly basis and 22 yr (1987-2008) on a monthly basis were used to develop and examine the performance of the proposed models. Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static and dynamic neural networks. Results showed that the MLP-NN neural network model is able to follow trends of the actual rainfall, however, not very accurately. RBFNN model achieved better accuracy than the MLP-NN model. Moreover, the forecasting accuracy of the IDNN model was better than that of static network during both training and testing stages, which proves a consistent level of accuracy with seen and unseen data.

UR - http://www.scopus.com/inward/record.url?scp=84859572047&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859572047&partnerID=8YFLogxK

U2 - 10.5194/hess-16-1151-2012

DO - 10.5194/hess-16-1151-2012

M3 - Article

AN - SCOPUS:84859572047

VL - 16

SP - 1151

EP - 1169

JO - Hydrology and Earth System Sciences

JF - Hydrology and Earth System Sciences

SN - 1027-5606

IS - 4

ER -