Clustering project management for drought regions determination: A case study in Serbia

Shahaboddin Shamshirband, Milan Gocić, Dalibor Petković, Hossein Javidnia, Siti Hafizah Ab Hamid, Zulkefli Mansor, Sultan Noman Qasem

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Analyses of drought regions require long-term historical data to ensure reliable drought indices estimate. Therefore, various indices have been used to measure different drought characteristics depending on research objectives. The present study investigates the application of clustering methods on the standardized precipitation index (SPI) at the 12-month timescale values in Serbia to detect district drought clusters. The principal component analysis (PCA) was applied to capture the drought patterns with similar drought features, while the cluster analysis was used as one of the major data analysis technique. Thus, three clustering algorithms namely fuzzy c-means (FCM), k-medoids and imperialist competitive algorithm (ICA) were analyzed in this research work. These algorithms are implemented by means of practical approach to segment the drought regions (clusters). In this way, three different drought clusters were detected. Statistical results indicate that the k-medoids clustering method was more effective and efficient than the FCM and ICA. The ICA clustering technique had the worst classification capability. The obtained results confirm usefulness of clustering methods for drought regionalization.

Original languageEnglish
Pages (from-to)57-65
Number of pages9
JournalAgricultural and Forest Meteorology
Volume200
DOIs
Publication statusPublished - 5 Jan 2015
Externally publishedYes

Fingerprint

project management
Serbia
drought
case studies
methodology
research work
regionalization
cluster analysis
data analysis
principal component analysis
timescale

Keywords

  • Clustering
  • Drought
  • Fuzzy c-means
  • Imperialist competitive algorithm
  • K-Medoids
  • Serbia

ASJC Scopus subject areas

  • Agronomy and Crop Science
  • Forestry
  • Atmospheric Science
  • Global and Planetary Change

Cite this

Clustering project management for drought regions determination : A case study in Serbia. / Shamshirband, Shahaboddin; Gocić, Milan; Petković, Dalibor; Javidnia, Hossein; Ab Hamid, Siti Hafizah; Mansor, Zulkefli; Qasem, Sultan Noman.

In: Agricultural and Forest Meteorology, Vol. 200, 05.01.2015, p. 57-65.

Research output: Contribution to journalArticle

Shamshirband, Shahaboddin ; Gocić, Milan ; Petković, Dalibor ; Javidnia, Hossein ; Ab Hamid, Siti Hafizah ; Mansor, Zulkefli ; Qasem, Sultan Noman. / Clustering project management for drought regions determination : A case study in Serbia. In: Agricultural and Forest Meteorology. 2015 ; Vol. 200. pp. 57-65.
@article{639c468e135f4133b31496ad91583a79,
title = "Clustering project management for drought regions determination: A case study in Serbia",
abstract = "Analyses of drought regions require long-term historical data to ensure reliable drought indices estimate. Therefore, various indices have been used to measure different drought characteristics depending on research objectives. The present study investigates the application of clustering methods on the standardized precipitation index (SPI) at the 12-month timescale values in Serbia to detect district drought clusters. The principal component analysis (PCA) was applied to capture the drought patterns with similar drought features, while the cluster analysis was used as one of the major data analysis technique. Thus, three clustering algorithms namely fuzzy c-means (FCM), k-medoids and imperialist competitive algorithm (ICA) were analyzed in this research work. These algorithms are implemented by means of practical approach to segment the drought regions (clusters). In this way, three different drought clusters were detected. Statistical results indicate that the k-medoids clustering method was more effective and efficient than the FCM and ICA. The ICA clustering technique had the worst classification capability. The obtained results confirm usefulness of clustering methods for drought regionalization.",
keywords = "Clustering, Drought, Fuzzy c-means, Imperialist competitive algorithm, K-Medoids, Serbia",
author = "Shahaboddin Shamshirband and Milan Gocić and Dalibor Petković and Hossein Javidnia and {Ab Hamid}, {Siti Hafizah} and Zulkefli Mansor and Qasem, {Sultan Noman}",
year = "2015",
month = "1",
day = "5",
doi = "10.1016/j.agrformet.2014.09.020",
language = "English",
volume = "200",
pages = "57--65",
journal = "Agricultural and Forest Meteorology",
issn = "0168-1923",
publisher = "Elsevier",

}

TY - JOUR

T1 - Clustering project management for drought regions determination

T2 - A case study in Serbia

AU - Shamshirband, Shahaboddin

AU - Gocić, Milan

AU - Petković, Dalibor

AU - Javidnia, Hossein

AU - Ab Hamid, Siti Hafizah

AU - Mansor, Zulkefli

AU - Qasem, Sultan Noman

PY - 2015/1/5

Y1 - 2015/1/5

N2 - Analyses of drought regions require long-term historical data to ensure reliable drought indices estimate. Therefore, various indices have been used to measure different drought characteristics depending on research objectives. The present study investigates the application of clustering methods on the standardized precipitation index (SPI) at the 12-month timescale values in Serbia to detect district drought clusters. The principal component analysis (PCA) was applied to capture the drought patterns with similar drought features, while the cluster analysis was used as one of the major data analysis technique. Thus, three clustering algorithms namely fuzzy c-means (FCM), k-medoids and imperialist competitive algorithm (ICA) were analyzed in this research work. These algorithms are implemented by means of practical approach to segment the drought regions (clusters). In this way, three different drought clusters were detected. Statistical results indicate that the k-medoids clustering method was more effective and efficient than the FCM and ICA. The ICA clustering technique had the worst classification capability. The obtained results confirm usefulness of clustering methods for drought regionalization.

AB - Analyses of drought regions require long-term historical data to ensure reliable drought indices estimate. Therefore, various indices have been used to measure different drought characteristics depending on research objectives. The present study investigates the application of clustering methods on the standardized precipitation index (SPI) at the 12-month timescale values in Serbia to detect district drought clusters. The principal component analysis (PCA) was applied to capture the drought patterns with similar drought features, while the cluster analysis was used as one of the major data analysis technique. Thus, three clustering algorithms namely fuzzy c-means (FCM), k-medoids and imperialist competitive algorithm (ICA) were analyzed in this research work. These algorithms are implemented by means of practical approach to segment the drought regions (clusters). In this way, three different drought clusters were detected. Statistical results indicate that the k-medoids clustering method was more effective and efficient than the FCM and ICA. The ICA clustering technique had the worst classification capability. The obtained results confirm usefulness of clustering methods for drought regionalization.

KW - Clustering

KW - Drought

KW - Fuzzy c-means

KW - Imperialist competitive algorithm

KW - K-Medoids

KW - Serbia

UR - http://www.scopus.com/inward/record.url?scp=84907993839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907993839&partnerID=8YFLogxK

U2 - 10.1016/j.agrformet.2014.09.020

DO - 10.1016/j.agrformet.2014.09.020

M3 - Article

AN - SCOPUS:84907993839

VL - 200

SP - 57

EP - 65

JO - Agricultural and Forest Meteorology

JF - Agricultural and Forest Meteorology

SN - 0168-1923

ER -