Comparison between mixed probability models and Markov chain models for weekly dry and wet spells in peninsular Malaysia

Sayang Mohd Deni, Abdul Aziz Jemain

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

Abstract

Information on the best probability models in representing the weekly distribution of dry and wet spells is increasingly important in various sectors including hydrological and water resource management. The application of the mixed probability models such as the mixture among the log series and geometric, Poisson as well as the truncated distributions is considered in fitting the observed data sets. In addition, the success of the higher order Markov chain models up to the tenth order is also compared with the mixed probability models. The performance of the best fitted models is assessed by using the Kolmogorov-Smirnov goodness-of-fit test in twelve selected rainfall stations from 1975 to 2010. The findings indicate that the mixture log series and truncated Poisson (MLTPD) are found to successfully fit the observed distribution of the weekly dry spells, while, the mixture log series and truncated geometric distribution (MGTPD) are more appropriate for the wet spells. The results obtained from the best fitted probability models will be used to produce the weekly dry and wet spells indices such as the mean and the maximum length of spells as well as the frequency of short and long spells.

Original languageEnglish
Title of host publicationProceedings of the World Congress on Engineering 2012, WCE 2012
EditorsLen Gelman, Andrew Hunter, A. M. Korsunsky, S. I. Ao, David WL Hukins
PublisherNewswood Limited
Pages318-323
Number of pages6
Volume2197
ISBN (Print)9789881925138
Publication statusPublished - 1 Jan 2012
Event2012 World Congress on Engineering, WCE 2012 - London
Duration: 4 Jul 20126 Jul 2012

Other

Other2012 World Congress on Engineering, WCE 2012
CityLondon
Period4/7/126/7/12

Fingerprint

Markov processes
Water resources
Rain

Keywords

  • Dry wet spells
  • Kolmogorov-smirnov goodness-of-fit test
  • Markov chain models
  • Mixed probability models

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Deni, S. M., & Jemain, A. A. (2012). Comparison between mixed probability models and Markov chain models for weekly dry and wet spells in peninsular Malaysia. In L. Gelman, A. Hunter, A. M. Korsunsky, S. I. Ao, & D. WL. Hukins (Eds.), Proceedings of the World Congress on Engineering 2012, WCE 2012 (Vol. 2197, pp. 318-323). Newswood Limited.

Comparison between mixed probability models and Markov chain models for weekly dry and wet spells in peninsular Malaysia. / Deni, Sayang Mohd; Jemain, Abdul Aziz.

Proceedings of the World Congress on Engineering 2012, WCE 2012. ed. / Len Gelman; Andrew Hunter; A. M. Korsunsky; S. I. Ao; David WL Hukins. Vol. 2197 Newswood Limited, 2012. p. 318-323.

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

Deni, SM & Jemain, AA 2012, Comparison between mixed probability models and Markov chain models for weekly dry and wet spells in peninsular Malaysia. in L Gelman, A Hunter, AM Korsunsky, SI Ao & DWL Hukins (eds), Proceedings of the World Congress on Engineering 2012, WCE 2012. vol. 2197, Newswood Limited, pp. 318-323, 2012 World Congress on Engineering, WCE 2012, London, 4/7/12.
Deni SM, Jemain AA. Comparison between mixed probability models and Markov chain models for weekly dry and wet spells in peninsular Malaysia. In Gelman L, Hunter A, Korsunsky AM, Ao SI, Hukins DWL, editors, Proceedings of the World Congress on Engineering 2012, WCE 2012. Vol. 2197. Newswood Limited. 2012. p. 318-323
Deni, Sayang Mohd ; Jemain, Abdul Aziz. / Comparison between mixed probability models and Markov chain models for weekly dry and wet spells in peninsular Malaysia. Proceedings of the World Congress on Engineering 2012, WCE 2012. editor / Len Gelman ; Andrew Hunter ; A. M. Korsunsky ; S. I. Ao ; David WL Hukins. Vol. 2197 Newswood Limited, 2012. pp. 318-323
@inproceedings{b9dc3270371a417ca085781826c66094,
title = "Comparison between mixed probability models and Markov chain models for weekly dry and wet spells in peninsular Malaysia",
abstract = "Information on the best probability models in representing the weekly distribution of dry and wet spells is increasingly important in various sectors including hydrological and water resource management. The application of the mixed probability models such as the mixture among the log series and geometric, Poisson as well as the truncated distributions is considered in fitting the observed data sets. In addition, the success of the higher order Markov chain models up to the tenth order is also compared with the mixed probability models. The performance of the best fitted models is assessed by using the Kolmogorov-Smirnov goodness-of-fit test in twelve selected rainfall stations from 1975 to 2010. The findings indicate that the mixture log series and truncated Poisson (MLTPD) are found to successfully fit the observed distribution of the weekly dry spells, while, the mixture log series and truncated geometric distribution (MGTPD) are more appropriate for the wet spells. The results obtained from the best fitted probability models will be used to produce the weekly dry and wet spells indices such as the mean and the maximum length of spells as well as the frequency of short and long spells.",
keywords = "Dry wet spells, Kolmogorov-smirnov goodness-of-fit test, Markov chain models, Mixed probability models",
author = "Deni, {Sayang Mohd} and Jemain, {Abdul Aziz}",
year = "2012",
month = "1",
day = "1",
language = "English",
isbn = "9789881925138",
volume = "2197",
pages = "318--323",
editor = "Len Gelman and Andrew Hunter and Korsunsky, {A. M.} and Ao, {S. I.} and Hukins, {David WL}",
booktitle = "Proceedings of the World Congress on Engineering 2012, WCE 2012",
publisher = "Newswood Limited",

}

TY - GEN

T1 - Comparison between mixed probability models and Markov chain models for weekly dry and wet spells in peninsular Malaysia

AU - Deni, Sayang Mohd

AU - Jemain, Abdul Aziz

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Information on the best probability models in representing the weekly distribution of dry and wet spells is increasingly important in various sectors including hydrological and water resource management. The application of the mixed probability models such as the mixture among the log series and geometric, Poisson as well as the truncated distributions is considered in fitting the observed data sets. In addition, the success of the higher order Markov chain models up to the tenth order is also compared with the mixed probability models. The performance of the best fitted models is assessed by using the Kolmogorov-Smirnov goodness-of-fit test in twelve selected rainfall stations from 1975 to 2010. The findings indicate that the mixture log series and truncated Poisson (MLTPD) are found to successfully fit the observed distribution of the weekly dry spells, while, the mixture log series and truncated geometric distribution (MGTPD) are more appropriate for the wet spells. The results obtained from the best fitted probability models will be used to produce the weekly dry and wet spells indices such as the mean and the maximum length of spells as well as the frequency of short and long spells.

AB - Information on the best probability models in representing the weekly distribution of dry and wet spells is increasingly important in various sectors including hydrological and water resource management. The application of the mixed probability models such as the mixture among the log series and geometric, Poisson as well as the truncated distributions is considered in fitting the observed data sets. In addition, the success of the higher order Markov chain models up to the tenth order is also compared with the mixed probability models. The performance of the best fitted models is assessed by using the Kolmogorov-Smirnov goodness-of-fit test in twelve selected rainfall stations from 1975 to 2010. The findings indicate that the mixture log series and truncated Poisson (MLTPD) are found to successfully fit the observed distribution of the weekly dry spells, while, the mixture log series and truncated geometric distribution (MGTPD) are more appropriate for the wet spells. The results obtained from the best fitted probability models will be used to produce the weekly dry and wet spells indices such as the mean and the maximum length of spells as well as the frequency of short and long spells.

KW - Dry wet spells

KW - Kolmogorov-smirnov goodness-of-fit test

KW - Markov chain models

KW - Mixed probability models

UR - http://www.scopus.com/inward/record.url?scp=85051786003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051786003&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789881925138

VL - 2197

SP - 318

EP - 323

BT - Proceedings of the World Congress on Engineering 2012, WCE 2012

A2 - Gelman, Len

A2 - Hunter, Andrew

A2 - Korsunsky, A. M.

A2 - Ao, S. I.

A2 - Hukins, David WL

PB - Newswood Limited

ER -