Integration of Fuzzy C-Means and artificial neural network for short-term localized rainfall forecast in tropical climate

Noor Zuraidin Mohd-Safar, David Ndzi, David Sanders, Hassanuddin Mohamed Noor, Latifah Munirah Kamarudin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper evaluates the performance of a rainfall forecasting model. In this paper Artificial Neural Network (ANN) and Fuzzy C-Means (FCM) clustering algorithm are combined and used to forecast short-term localized rainfall in tropical climate. State forecast (raining or not raining) and value forecast (rain intensity) are tested using a number of trained networks. Different types of ANN structured were trained with a combination of multilayer perceptron with back propagation network. Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient training algorithm are used in the network training. Each neurons uses linear, logistic sigmoid and hyperbolic tangent sigmoid as transfer function. Input parameter preliminary analysis, data cleaning and FCM clustering were used to prepare input data for the ANN forecast model. Meteorological data such as atmospheric pressure, temperature, dew point, humidity and wind speed have been used as input parameters. The predicted rainfall forecast for 1 to 6 h ahead are compared and analyzed. 1 h ahead for state and value forecast yield high accuracy. Result shows that, the combined of FCM-ANN forecast model produces better accuracy compared to a basic ANN forecast model.

Original languageEnglish
Title of host publicationProceedings of SAI Intelligent Systems Conference (IntelliSys) 2016
PublisherSpringer International Publishing AG
Pages499-516
ISBN (Electronic)978-3-319-56991-8
ISBN (Print)978-3-319-56990-1
DOIs
Publication statusPublished - 2018
Externally publishedYes

Publication series

NameLecture Notes in Networks and Systems
PublisherSpringer
ISSN (Print)2367-3370

Fingerprint

artificial neural network
rainfall
dew point
forecast
tropical climate
back propagation
transfer function
atmospheric pressure
logistics
humidity
wind velocity
temperature

Cite this

Mohd-Safar, N. Z., Ndzi, D., Sanders, D., Mohamed Noor, H., & Kamarudin, L. M. (2018). Integration of Fuzzy C-Means and artificial neural network for short-term localized rainfall forecast in tropical climate. In Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016 (pp. 499-516). (Lecture Notes in Networks and Systems). Springer International Publishing AG. https://doi.org/10.1007/978-3-319-56991-8_38
Mohd-Safar, Noor Zuraidin ; Ndzi, David ; Sanders, David ; Mohamed Noor, Hassanuddin ; Kamarudin, Latifah Munirah . / Integration of Fuzzy C-Means and artificial neural network for short-term localized rainfall forecast in tropical climate. Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016. Springer International Publishing AG, 2018. pp. 499-516 (Lecture Notes in Networks and Systems).
@inproceedings{7858d0bf53354db5adffe9ae4fa9cc4b,
title = "Integration of Fuzzy C-Means and artificial neural network for short-term localized rainfall forecast in tropical climate",
abstract = "This paper evaluates the performance of a rainfall forecasting model. In this paper Artificial Neural Network (ANN) and Fuzzy C-Means (FCM) clustering algorithm are combined and used to forecast short-term localized rainfall in tropical climate. State forecast (raining or not raining) and value forecast (rain intensity) are tested using a number of trained networks. Different types of ANN structured were trained with a combination of multilayer perceptron with back propagation network. Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient training algorithm are used in the network training. Each neurons uses linear, logistic sigmoid and hyperbolic tangent sigmoid as transfer function. Input parameter preliminary analysis, data cleaning and FCM clustering were used to prepare input data for the ANN forecast model. Meteorological data such as atmospheric pressure, temperature, dew point, humidity and wind speed have been used as input parameters. The predicted rainfall forecast for 1 to 6 h ahead are compared and analyzed. 1 h ahead for state and value forecast yield high accuracy. Result shows that, the combined of FCM-ANN forecast model produces better accuracy compared to a basic ANN forecast model.",
author = "Mohd-Safar, {Noor Zuraidin} and David Ndzi and David Sanders and {Mohamed Noor}, Hassanuddin and Kamarudin, {Latifah Munirah}",
year = "2018",
doi = "10.1007/978-3-319-56991-8_38",
language = "English",
isbn = "978-3-319-56990-1",
series = "Lecture Notes in Networks and Systems",
publisher = "Springer International Publishing AG",
pages = "499--516",
booktitle = "Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016",
address = "Switzerland",

}

Mohd-Safar, NZ, Ndzi, D, Sanders, D, Mohamed Noor, H & Kamarudin, LM 2018, Integration of Fuzzy C-Means and artificial neural network for short-term localized rainfall forecast in tropical climate. in Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016. Lecture Notes in Networks and Systems, Springer International Publishing AG, pp. 499-516. https://doi.org/10.1007/978-3-319-56991-8_38

Integration of Fuzzy C-Means and artificial neural network for short-term localized rainfall forecast in tropical climate. / Mohd-Safar, Noor Zuraidin; Ndzi, David; Sanders, David; Mohamed Noor, Hassanuddin ; Kamarudin, Latifah Munirah .

Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016. Springer International Publishing AG, 2018. p. 499-516 (Lecture Notes in Networks and Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Integration of Fuzzy C-Means and artificial neural network for short-term localized rainfall forecast in tropical climate

AU - Mohd-Safar, Noor Zuraidin

AU - Ndzi, David

AU - Sanders, David

AU - Mohamed Noor, Hassanuddin

AU - Kamarudin, Latifah Munirah

PY - 2018

Y1 - 2018

N2 - This paper evaluates the performance of a rainfall forecasting model. In this paper Artificial Neural Network (ANN) and Fuzzy C-Means (FCM) clustering algorithm are combined and used to forecast short-term localized rainfall in tropical climate. State forecast (raining or not raining) and value forecast (rain intensity) are tested using a number of trained networks. Different types of ANN structured were trained with a combination of multilayer perceptron with back propagation network. Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient training algorithm are used in the network training. Each neurons uses linear, logistic sigmoid and hyperbolic tangent sigmoid as transfer function. Input parameter preliminary analysis, data cleaning and FCM clustering were used to prepare input data for the ANN forecast model. Meteorological data such as atmospheric pressure, temperature, dew point, humidity and wind speed have been used as input parameters. The predicted rainfall forecast for 1 to 6 h ahead are compared and analyzed. 1 h ahead for state and value forecast yield high accuracy. Result shows that, the combined of FCM-ANN forecast model produces better accuracy compared to a basic ANN forecast model.

AB - This paper evaluates the performance of a rainfall forecasting model. In this paper Artificial Neural Network (ANN) and Fuzzy C-Means (FCM) clustering algorithm are combined and used to forecast short-term localized rainfall in tropical climate. State forecast (raining or not raining) and value forecast (rain intensity) are tested using a number of trained networks. Different types of ANN structured were trained with a combination of multilayer perceptron with back propagation network. Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient training algorithm are used in the network training. Each neurons uses linear, logistic sigmoid and hyperbolic tangent sigmoid as transfer function. Input parameter preliminary analysis, data cleaning and FCM clustering were used to prepare input data for the ANN forecast model. Meteorological data such as atmospheric pressure, temperature, dew point, humidity and wind speed have been used as input parameters. The predicted rainfall forecast for 1 to 6 h ahead are compared and analyzed. 1 h ahead for state and value forecast yield high accuracy. Result shows that, the combined of FCM-ANN forecast model produces better accuracy compared to a basic ANN forecast model.

U2 - 10.1007/978-3-319-56991-8_38

DO - 10.1007/978-3-319-56991-8_38

M3 - Conference contribution

SN - 978-3-319-56990-1

T3 - Lecture Notes in Networks and Systems

SP - 499

EP - 516

BT - Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016

PB - Springer International Publishing AG

ER -

Mohd-Safar NZ, Ndzi D, Sanders D, Mohamed Noor H, Kamarudin LM. Integration of Fuzzy C-Means and artificial neural network for short-term localized rainfall forecast in tropical climate. In Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016. Springer International Publishing AG. 2018. p. 499-516. (Lecture Notes in Networks and Systems). https://doi.org/10.1007/978-3-319-56991-8_38