Open AccessSoft and hard clustering methods for delineation of hydrological homogeneous regions in the southern strip of the C aspian S ea W atershed
Author(s) -
Chavoshi S.,
Azmin Sulaiman W.N.,
Saghafian B.,
Sulaiman MD. N.B.,
Latifah A.M.
Publication year - 2012
Publication title -
journal of flood risk management
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.049
H-Index - 36
ISSN - 1753-318X
DOI - 10.1111/j.1753-318x.2012.01149.x
Subject(s) - regionalisation , cluster analysis , homogeneous , cluster (spacecraft) , single linkage clustering , computer science , data mining , mathematics , geography , correlation clustering , statistics , combinatorics , cure data clustering algorithm , economic geography , programming language
Regionalisation is a fundamental task for transferring hydrological information from gauged to un‐gauged catchments. This study employs several soft and hard clustering approaches for regionalisation of the 61 catchments located in the southern strip of the C aspian S ea W atershed. Factor analysis using P rincipal C omponent A nalysis resulted to four out of 16 catchment's attributes relating to flooding which were then used for regionalisation. H ierarchical and Non‐ H ierarchical C lustering, K ‐Means, F uzzy C ‐Means and K ohonen methods were studied and compared by L ‐ M oment tests. While in hard clustering approach, distinct clusters of catchments were formed, soft clustering techniques allocated catchments to more than one cluster according to their membership probability. The performance of different clustering methods resulted to the similar number of homogeneous groups. However, the number of sites allocated to the clusters is different. Hard clustering resulted in three clusters at 38, 10 and 13 sites, while Soft clustering allocated 26, 20 and 15 sites to the clusters, respectively. Results indicate a superiority of the soft clustering in the study area where deriving hydrologic groups by hard clustering is problematic.