Statistical downscaling of precipitation using inclusive multiple modelling (IMM) at two levels

Topical research on hydrological behaviour of climate change in terms of downscaling of monthly precipitation is investigated in this paper by formulating an inclusive multiple modelling (IMM) strategy. IMM strategies manage multiple models at two levels and the paper uses statistical downscaling mo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sina Sadeghfam, Rahman Khatibi, Tara Moradian, Rasoul Daneshfaraz
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	artificial intelligence models downscaling inclusive multiple modelling (imm) precipitation projection Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/3832bb5598174372b6bd455553654e21
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3832bb5598174372b6bd455553654e21
record_format	dspace
spelling	oai:doaj.org-article:3832bb5598174372b6bd455553654e212021-11-10T00:00:04ZStatistical downscaling of precipitation using inclusive multiple modelling (IMM) at two levels2040-22442408-935410.2166/wcc.2021.106https://doaj.org/article/3832bb5598174372b6bd455553654e212021-11-01T00:00:00Zhttp://jwcc.iwaponline.com/content/12/7/3373https://doaj.org/toc/2040-2244https://doaj.org/toc/2408-9354Topical research on hydrological behaviour of climate change in terms of downscaling of monthly precipitation is investigated in this paper by formulating an inclusive multiple modelling (IMM) strategy. IMM strategies manage multiple models at two levels and the paper uses statistical downscaling model, Sugeno fuzzy logic and support vector machine at Level 1 and feeds their outputs to a neuro-fuzzy model at Level 2. In the downscaling stage, large-scale NCEP (National Centres for Environmental Prediction)/NCAR (National Centre for Atmospheric Research) data are used for a station with local data record from 1961 to 2005 for training and testing Level 1 models. The results are found to be ‘fit-for-purpose’, but the variations between them signify some room for improvements. The model at Level 2 combines outputs of those at Level 1 and produces Level 2 results, which improve compared with those at the Level 1 models in terms of dispersion of residual errors. In this way, IMM provides a more defensible modelling strategy for application in the projection stage. The comparison between observed and projected precipitation indicates that precipitation will be likely to reduce compared with observed precipitation in cold seasons (October–February), but the projected precipitation will be likely to increase slightly in wet seasons (April and May). HIGHLIGHTS Inclusive multiple modelling (IMM) is formulated for the downscaling of precipitation.; IMM manages multiple regression and artificial intelligence models at two levels.; Performances of IMM are improved over Level 1 models in the downscaling stage.; IMM provides a more defensible strategy for application in the projection stage.;Sina SadeghfamRahman KhatibiTara MoradianRasoul DaneshfarazIWA Publishingarticleartificial intelligence modelsdownscalinginclusive multiple modelling (imm)precipitationprojectionEnvironmental technology. Sanitary engineeringTD1-1066Environmental sciencesGE1-350ENJournal of Water and Climate Change, Vol 12, Iss 7, Pp 3373-3387 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	artificial intelligence models downscaling inclusive multiple modelling (imm) precipitation projection Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350
spellingShingle	artificial intelligence models downscaling inclusive multiple modelling (imm) precipitation projection Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350 Sina Sadeghfam Rahman Khatibi Tara Moradian Rasoul Daneshfaraz Statistical downscaling of precipitation using inclusive multiple modelling (IMM) at two levels
description	Topical research on hydrological behaviour of climate change in terms of downscaling of monthly precipitation is investigated in this paper by formulating an inclusive multiple modelling (IMM) strategy. IMM strategies manage multiple models at two levels and the paper uses statistical downscaling model, Sugeno fuzzy logic and support vector machine at Level 1 and feeds their outputs to a neuro-fuzzy model at Level 2. In the downscaling stage, large-scale NCEP (National Centres for Environmental Prediction)/NCAR (National Centre for Atmospheric Research) data are used for a station with local data record from 1961 to 2005 for training and testing Level 1 models. The results are found to be ‘fit-for-purpose’, but the variations between them signify some room for improvements. The model at Level 2 combines outputs of those at Level 1 and produces Level 2 results, which improve compared with those at the Level 1 models in terms of dispersion of residual errors. In this way, IMM provides a more defensible modelling strategy for application in the projection stage. The comparison between observed and projected precipitation indicates that precipitation will be likely to reduce compared with observed precipitation in cold seasons (October–February), but the projected precipitation will be likely to increase slightly in wet seasons (April and May). HIGHLIGHTS Inclusive multiple modelling (IMM) is formulated for the downscaling of precipitation.; IMM manages multiple regression and artificial intelligence models at two levels.; Performances of IMM are improved over Level 1 models in the downscaling stage.; IMM provides a more defensible strategy for application in the projection stage.;
format	article
author	Sina Sadeghfam Rahman Khatibi Tara Moradian Rasoul Daneshfaraz
author_facet	Sina Sadeghfam Rahman Khatibi Tara Moradian Rasoul Daneshfaraz
author_sort	Sina Sadeghfam
title	Statistical downscaling of precipitation using inclusive multiple modelling (IMM) at two levels
title_short	Statistical downscaling of precipitation using inclusive multiple modelling (IMM) at two levels
title_full	Statistical downscaling of precipitation using inclusive multiple modelling (IMM) at two levels
title_fullStr	Statistical downscaling of precipitation using inclusive multiple modelling (IMM) at two levels
title_full_unstemmed	Statistical downscaling of precipitation using inclusive multiple modelling (IMM) at two levels
title_sort	statistical downscaling of precipitation using inclusive multiple modelling (imm) at two levels
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/3832bb5598174372b6bd455553654e21
work_keys_str_mv	AT sinasadeghfam statisticaldownscalingofprecipitationusinginclusivemultiplemodellingimmattwolevels AT rahmankhatibi statisticaldownscalingofprecipitationusinginclusivemultiplemodellingimmattwolevels AT taramoradian statisticaldownscalingofprecipitationusinginclusivemultiplemodellingimmattwolevels AT rasouldaneshfaraz statisticaldownscalingofprecipitationusinginclusivemultiplemodellingimmattwolevels
_version_	1718440734836654080

Statistical downscaling of precipitation using inclusive multiple modelling (IMM) at two levels

Ejemplares similares