Cover Image

Label Propagation Method for Catchment Classification in Australia

Catchment classification has been one of the most important study in hydrology. There are many reasons of catchment classification studies has been done but most importantly, is for prediction of ungauged basin (PUB), among other purposes. There exist numerous approaches for classification, with dif...

Full description

Saved in:
Bibliographic Details
Main Author: Siti Aisyah Tumiran
Format: Proceedings
Language:English
English
Published: Faculty of Science & Natural Resources, UMS 2022
Subjects:
DU80-398 Australia
GB651-2998 Hydrology. Water
Online Access:https://eprints.ums.edu.my/id/eprint/40590/1/ABSTRACT.pdf
https://eprints.ums.edu.my/id/eprint/40590/2/FULL%20TEXT.pdf
https://eprints.ums.edu.my/id/eprint/40590/
https://www.ums.edu.my/fssa/index.php/research/conference-publication
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ums.eprints.40590
record_format eprints
spelling my.ums.eprints.405902024-08-09T00:21:06Z https://eprints.ums.edu.my/id/eprint/40590/ Label Propagation Method for Catchment Classification in Australia Siti Aisyah Tumiran DU80-398 Australia GB651-2998 Hydrology. Water Catchment classification has been one of the most important study in hydrology. There are many reasons of catchment classification studies has been done but most importantly, is for prediction of ungauged basin (PUB), among other purposes. There exist numerous approaches for classification, with different bases and assumptions, which have been applied for catchment classification. The concepts of complex networks, and particularly community structure, have emerged as important tools for classification, and are currently gaining attention in catchment classification. Therefore, in this present study, the community structure method particularly label propagation method, which every node is denoted with a unique label and at every step, each node adopts the label that most of its neighbors currently have. Then, densely connected groups of nodes form a consensus on a unique label iteratively to form communities. A network of 218 monthly streamflow stations across Australia are considered for catchment classification using the proposed method. The influence of correlation thresholds that exhibit the strength of connection between the stream flows which range from 0 to 1 is also examined. Hence, there are four threshold values are selected (T = 0.65, 0.7, 0.75 and 0.8) and the communities formed with each selected threshold value are interpreted. The results also reveal that communities identified from Australia stream flows using label propagation are best represent using threshold value of 0.8, based on the region boundaries. Faculty of Science & Natural Resources, UMS 2022 Proceedings PeerReviewed text en https://eprints.ums.edu.my/id/eprint/40590/1/ABSTRACT.pdf text en https://eprints.ums.edu.my/id/eprint/40590/2/FULL%20TEXT.pdf Siti Aisyah Tumiran (2022) Label Propagation Method for Catchment Classification in Australia. https://www.ums.edu.my/fssa/index.php/research/conference-publication
institution Universiti Malaysia Sabah
building UMS Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Sabah
content_source UMS Institutional Repository
url_provider http://eprints.ums.edu.my/
language English
English
topic DU80-398 Australia
GB651-2998 Hydrology. Water
spellingShingle DU80-398 Australia
GB651-2998 Hydrology. Water
Siti Aisyah Tumiran
Label Propagation Method for Catchment Classification in Australia
description Catchment classification has been one of the most important study in hydrology. There are many reasons of catchment classification studies has been done but most importantly, is for prediction of ungauged basin (PUB), among other purposes. There exist numerous approaches for classification, with different bases and assumptions, which have been applied for catchment classification. The concepts of complex networks, and particularly community structure, have emerged as important tools for classification, and are currently gaining attention in catchment classification. Therefore, in this present study, the community structure method particularly label propagation method, which every node is denoted with a unique label and at every step, each node adopts the label that most of its neighbors currently have. Then, densely connected groups of nodes form a consensus on a unique label iteratively to form communities. A network of 218 monthly streamflow stations across Australia are considered for catchment classification using the proposed method. The influence of correlation thresholds that exhibit the strength of connection between the stream flows which range from 0 to 1 is also examined. Hence, there are four threshold values are selected (T = 0.65, 0.7, 0.75 and 0.8) and the communities formed with each selected threshold value are interpreted. The results also reveal that communities identified from Australia stream flows using label propagation are best represent using threshold value of 0.8, based on the region boundaries.
format Proceedings
author Siti Aisyah Tumiran
author_facet Siti Aisyah Tumiran
author_sort Siti Aisyah Tumiran
title Label Propagation Method for Catchment Classification in Australia
title_short Label Propagation Method for Catchment Classification in Australia
title_full Label Propagation Method for Catchment Classification in Australia
title_fullStr Label Propagation Method for Catchment Classification in Australia
title_full_unstemmed Label Propagation Method for Catchment Classification in Australia
title_sort label propagation method for catchment classification in australia
publisher Faculty of Science & Natural Resources, UMS
publishDate 2022
url https://eprints.ums.edu.my/id/eprint/40590/1/ABSTRACT.pdf
https://eprints.ums.edu.my/id/eprint/40590/2/FULL%20TEXT.pdf
https://eprints.ums.edu.my/id/eprint/40590/
https://www.ums.edu.my/fssa/index.php/research/conference-publication
_version_ 1807050427478310912
score 13.211869

Similar Items