Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh

A model output statistics (MOS) downscaling approach based on support vector machine (SVM) is proposed in this study for the projection of spatial and temporal changes in rainfall of Bangladesh. A combination of past performance assessment and envelope-based methods is used for the selection of GCM...

Full description

Saved in:
Bibliographic Details
Main Authors: Pour, Sahar Hadi, Shahid, Shamsuddin, Chung, Eun Sung, Wang, Xiao Jun
Format: Article
Published: Elsevier Ltd 2018
Subjects:
Online Access:http://eprints.utm.my/id/eprint/84447/
http://dx.doi.org/10.1016/j.atmosres.2018.06.006
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.84447
record_format eprints
spelling my.utm.844472020-01-11T07:08:19Z http://eprints.utm.my/id/eprint/84447/ Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh Pour, Sahar Hadi Shahid, Shamsuddin Chung, Eun Sung Wang, Xiao Jun TA Engineering (General). Civil engineering (General) A model output statistics (MOS) downscaling approach based on support vector machine (SVM) is proposed in this study for the projection of spatial and temporal changes in rainfall of Bangladesh. A combination of past performance assessment and envelope-based methods is used for the selection of GCM ensemble from Coupled Model Intercomparison Project phase 5 (CMIP5). Gauge-based gridded monthly rainfall data of Global Precipitation Climatological Center (GPCC) is used as a reference for downscaling and projection of GCM rainfall at regular grid intervals. The obtained results reveal the ability of SVM-based MOS models to replicate the temporal variation and distribution of GPCC rainfall efficiently. The ensemble mean of selected GCM projections downscaled using MOS models show changes in annual precipitation in the range of −4.2% to 24.6% in Bangladesh under four Representative Concentration Pathways (RCP) scenarios. Annual rainfalls are projected to increase more in the western part (5.1% to 24.6%) where average annual rainfall is relatively low, and less in the eastern part (−4.2 to 12.4%) where average annual rainfall is relatively high, which indicates more homogeneity in the spatial distribution of rainfall in Bangladesh in future. A higher increase in rainfall is projected during monsoon compared to other seasons, which indicates more concentration of rainfall in Bangladesh during monsoon. Elsevier Ltd 2018-11 Article PeerReviewed Pour, Sahar Hadi and Shahid, Shamsuddin and Chung, Eun Sung and Wang, Xiao Jun (2018) Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh. Atmospheric Research, 213 . pp. 149-162. ISSN 0169-8095 http://dx.doi.org/10.1016/j.atmosres.2018.06.006
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic TA Engineering (General). Civil engineering (General)
spellingShingle TA Engineering (General). Civil engineering (General)
Pour, Sahar Hadi
Shahid, Shamsuddin
Chung, Eun Sung
Wang, Xiao Jun
Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh
description A model output statistics (MOS) downscaling approach based on support vector machine (SVM) is proposed in this study for the projection of spatial and temporal changes in rainfall of Bangladesh. A combination of past performance assessment and envelope-based methods is used for the selection of GCM ensemble from Coupled Model Intercomparison Project phase 5 (CMIP5). Gauge-based gridded monthly rainfall data of Global Precipitation Climatological Center (GPCC) is used as a reference for downscaling and projection of GCM rainfall at regular grid intervals. The obtained results reveal the ability of SVM-based MOS models to replicate the temporal variation and distribution of GPCC rainfall efficiently. The ensemble mean of selected GCM projections downscaled using MOS models show changes in annual precipitation in the range of −4.2% to 24.6% in Bangladesh under four Representative Concentration Pathways (RCP) scenarios. Annual rainfalls are projected to increase more in the western part (5.1% to 24.6%) where average annual rainfall is relatively low, and less in the eastern part (−4.2 to 12.4%) where average annual rainfall is relatively high, which indicates more homogeneity in the spatial distribution of rainfall in Bangladesh in future. A higher increase in rainfall is projected during monsoon compared to other seasons, which indicates more concentration of rainfall in Bangladesh during monsoon.
format Article
author Pour, Sahar Hadi
Shahid, Shamsuddin
Chung, Eun Sung
Wang, Xiao Jun
author_facet Pour, Sahar Hadi
Shahid, Shamsuddin
Chung, Eun Sung
Wang, Xiao Jun
author_sort Pour, Sahar Hadi
title Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh
title_short Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh
title_full Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh
title_fullStr Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh
title_full_unstemmed Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh
title_sort model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of bangladesh
publisher Elsevier Ltd
publishDate 2018
url http://eprints.utm.my/id/eprint/84447/
http://dx.doi.org/10.1016/j.atmosres.2018.06.006
_version_ 1657487658941677568
score 13.18916