Using multi-model ensembles of CMIP5 global climate models to reproduce observed monthly rainfall and temperature with machine learning methods in Australia

Wang, B; Zheng, L; Liu, DL; Ji, F; Clark, A; Yu, Q

Using multi-model ensembles of CMIP5 global climate models to reproduce observed monthly rainfall and temperature with machine learning methods in Australia

Wang, B Zheng, L Liu, DL Ji, F Clark, A Yu, Q

Permalink

Publication Type:: Journal Article
Citation:: International Journal of Climatology, 2018, 38 (13), pp. 4891 - 4902
Issue Date:: 2018-11-15

Closed Access

	Filename	Description	Size
	Wang_et_al-2018-International_Journal_of_Climatology.pdf	Published Version	2.93 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, B	en_US
dc.contributor.author	Zheng, L	en_US
dc.contributor.author	Liu, DL	en_US
dc.contributor.author	Ji, F	en_US
dc.contributor.author	Clark, A	en_US
dc.contributor.author	Yu, Q https://orcid.org/0000-0001-6950-1821	en_US
dc.date.issued	2018-11-15	en_US
dc.identifier.citation	International Journal of Climatology, 2018, 38 (13), pp. 4891 - 4902	en_US
dc.identifier.issn	0899-8418	en_US
dc.identifier.uri	http://hdl.handle.net/10453/131106
dc.description.abstract	© 2018 Royal Meteorological Society Global climate models (GCMs) are useful tools for assessing climate change impacts on temperature and rainfall. Although climate data from various GCMs have been increasingly used in climate change impact studies, GCMs configurations and module characteristics vary from one to another. Therefore, it is crucial to assess different GCMs to confirm the extent to which they can reproduce the observed temperature and rainfall. Rather than assessing the interdependence of each GCM, the purpose of this study is to compare the capacity of four different multi-model ensemble (MME) methods (random forest [RF], support vector machine [SVM], Bayesian model averaging [BMA] and the arithmetic ensemble mean [EM]) in reproducing observed monthly rainfall and temperature. Of these four methods, the RF and SVM demonstrated a significant improvement over EM and BMA in terms of performance criteria. The relative importance of each GCM based on the RF ensemble in reproducing rainfall and temperature could also be ranked. We compared the GCMs importance and Taylor skill score and found that their correlation was 0.95 for temperature and 0.54 for rainfall. Our results also demonstrated that the number of GCMs ensemble simulations could be reduced from 33 to 25 in RF model while maintaining predictive error less than 2%. Having such a representative subset of simulations could reduce computational costs for climate impact modelling and maintain the quality of ensemble at the same time. We conclude that machine learning MME could be efficient and useful with improved accuracy in reproducing historical climate variables.	en_US
dc.relation.ispartof	International Journal of Climatology	en_US
dc.relation.isbasedon	10.1002/joc.5705	en_US
dc.subject.classification	Meteorology & Atmospheric Sciences	en_US
dc.title	Using multi-model ensembles of CMIP5 global climate models to reproduce observed monthly rainfall and temperature with machine learning methods in Australia	en_US
dc.type	Journal Article
utslib.citation.volume	13	en_US
utslib.citation.volume	38	en_US
utslib.for	0401 Atmospheric Sciences	en_US
utslib.for	0905 Civil Engineering	en_US
utslib.for	0907 Environmental Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Life Sciences
utslib.copyright.status	closed_access
pubs.issue	13	en_US
pubs.publication-status	Published	en_US
pubs.volume	38	en_US

Abstract:

© 2018 Royal Meteorological Society Global climate models (GCMs) are useful tools for assessing climate change impacts on temperature and rainfall. Although climate data from various GCMs have been increasingly used in climate change impact studies, GCMs configurations and module characteristics vary from one to another. Therefore, it is crucial to assess different GCMs to confirm the extent to which they can reproduce the observed temperature and rainfall. Rather than assessing the interdependence of each GCM, the purpose of this study is to compare the capacity of four different multi-model ensemble (MME) methods (random forest [RF], support vector machine [SVM], Bayesian model averaging [BMA] and the arithmetic ensemble mean [EM]) in reproducing observed monthly rainfall and temperature. Of these four methods, the RF and SVM demonstrated a significant improvement over EM and BMA in terms of performance criteria. The relative importance of each GCM based on the RF ensemble in reproducing rainfall and temperature could also be ranked. We compared the GCMs importance and Taylor skill score and found that their correlation was 0.95 for temperature and 0.54 for rainfall. Our results also demonstrated that the number of GCMs ensemble simulations could be reduced from 33 to 25 in RF model while maintaining predictive error less than 2%. Having such a representative subset of simulations could reduce computational costs for climate impact modelling and maintain the quality of ensemble at the same time. We conclude that machine learning MME could be efficient and useful with improved accuracy in reproducing historical climate variables.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/131106