Abstract

This study proposes the Sequential Pattern Discovery algorithms to solve weather prediction problem. A novel weather pattern discovery framework is presented to highlight the important processes in this work. Two algorithms are employed; namely episodes and sequential pattern mining algorithms. The episodes mining algorithm is introduced to find frequent episodes in rainfall sequences and sequential pattern mining algorithm to find relationship of patterns between weather stations. Real data are collected from ten rainfall stations of Selangor State, Malaysia. The sequential pattern algorithm is applied to extract the relationship between ten rainfall stations in 33 years periods of time. The patterns are evaluated experimentally by support and confidence values while some specific rules are mapped to the location of stations and analysed for more verification. The proposed study produces valuable patterns of weather and preserves important knowledge for weather prediction.

Original languageEnglish
Pages (from-to)223-240
Number of pages18
JournalStudies in Computational Intelligence
Volume647
DOIs
Publication statusPublished - 2016

Fingerprint

Rain

Keywords

  • Episodes mining
  • Pattern discovery
  • Sequential patterns

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

@article{aca9064ec18948d79e1e30294886d15d,
title = "Sequential pattern discovery for weather prediction problem",
abstract = "This study proposes the Sequential Pattern Discovery algorithms to solve weather prediction problem. A novel weather pattern discovery framework is presented to highlight the important processes in this work. Two algorithms are employed; namely episodes and sequential pattern mining algorithms. The episodes mining algorithm is introduced to find frequent episodes in rainfall sequences and sequential pattern mining algorithm to find relationship of patterns between weather stations. Real data are collected from ten rainfall stations of Selangor State, Malaysia. The sequential pattern algorithm is applied to extract the relationship between ten rainfall stations in 33 years periods of time. The patterns are evaluated experimentally by support and confidence values while some specific rules are mapped to the location of stations and analysed for more verification. The proposed study produces valuable patterns of weather and preserves important knowledge for weather prediction.",
keywords = "Episodes mining, Pattern discovery, Sequential patterns",
author = "Almahdi Alshareef and {Abu Bakar}, Azuraliza and Hamdan, {Abdul Razak} and {Syed Abdullah}, {Sharifah Mastura} and Othman Jaafar",
year = "2016",
doi = "10.1007/978-3-319-33353-3_12",
language = "English",
volume = "647",
pages = "223--240",
journal = "Studies in Computational Intelligence",
issn = "1860-949X",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - Sequential pattern discovery for weather prediction problem

AU - Alshareef, Almahdi

AU - Abu Bakar, Azuraliza

AU - Hamdan, Abdul Razak

AU - Syed Abdullah, Sharifah Mastura

AU - Jaafar, Othman

PY - 2016

Y1 - 2016

N2 - This study proposes the Sequential Pattern Discovery algorithms to solve weather prediction problem. A novel weather pattern discovery framework is presented to highlight the important processes in this work. Two algorithms are employed; namely episodes and sequential pattern mining algorithms. The episodes mining algorithm is introduced to find frequent episodes in rainfall sequences and sequential pattern mining algorithm to find relationship of patterns between weather stations. Real data are collected from ten rainfall stations of Selangor State, Malaysia. The sequential pattern algorithm is applied to extract the relationship between ten rainfall stations in 33 years periods of time. The patterns are evaluated experimentally by support and confidence values while some specific rules are mapped to the location of stations and analysed for more verification. The proposed study produces valuable patterns of weather and preserves important knowledge for weather prediction.

AB - This study proposes the Sequential Pattern Discovery algorithms to solve weather prediction problem. A novel weather pattern discovery framework is presented to highlight the important processes in this work. Two algorithms are employed; namely episodes and sequential pattern mining algorithms. The episodes mining algorithm is introduced to find frequent episodes in rainfall sequences and sequential pattern mining algorithm to find relationship of patterns between weather stations. Real data are collected from ten rainfall stations of Selangor State, Malaysia. The sequential pattern algorithm is applied to extract the relationship between ten rainfall stations in 33 years periods of time. The patterns are evaluated experimentally by support and confidence values while some specific rules are mapped to the location of stations and analysed for more verification. The proposed study produces valuable patterns of weather and preserves important knowledge for weather prediction.

KW - Episodes mining

KW - Pattern discovery

KW - Sequential patterns

UR - http://www.scopus.com/inward/record.url?scp=84991786776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991786776&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-33353-3_12

DO - 10.1007/978-3-319-33353-3_12

M3 - Article

AN - SCOPUS:84991786776

VL - 647

SP - 223

EP - 240

JO - Studies in Computational Intelligence

JF - Studies in Computational Intelligence

SN - 1860-949X

ER -