Climate Change Data Portal
DOI | 10.1016/j.atmosres.2019.104806 |
Multi-model ensemble predictions of precipitation and temperature using machine learning algorithms | |
Ahmed K.; Sachindra D.A.; Shahid S.; Iqbal Z.; Nawaz N.; Khan N. | |
发表日期 | 2020 |
ISSN | 0169-8095 |
卷号 | 236 |
英文摘要 | Multi-Model Ensembles (MMEs) are often employed to reduce the uncertainties related to GCM simulations/projections. The objective of this study was to evaluate the performance of MMEs developed using machine learning (ML) algorithms with different combinations of GCMs ranked based on their performance and determine the optimum number of GCMs to be included in an MME. In this study ML algorithms; Artificial Neural Network (ANN), K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Relevance Vector Machine (RVM) were used to develop MMEs for annual, monsoon and winter; precipitation (P), maximum (Tmax) and minimum (Tmin) temperature over Pakistan using 36 Coupled Model Intercomparison Project Phase 5 GCMs. GCMs were ranked using Taylor Skill Score for individual seasons and variables, and then using a comprehensive Rating Metric (RM) overall rank of each GCM was determined. It was found that, HadGEM2-AO is the most skilled GCM and IPSL-CM5B-LR is the least skilled GCMs in simulating the 3 climate variables. The performance of MMEs did not improve after the inclusion of about 18 top-ranked GCMs. Thus, it was understood that the optimum performance of MMEs is achieved when about 50% of the top-ranked GCMs are used. The inter-comparison of MMEs developed with ANN, KNN, SVM and RVM revealed that KNN and RVM-based MMEs show better skills. It was found that RVM yields MMEs which show smaller variations in performance over space unlike ANN which displayed large fluctuations in performance over space. KNN and RVM are recommended over SVM and ANN for the development of MMEs over Pakistan. © 2019 Elsevier B.V. |
英文关键词 | General circulation models; Machine learning algorithms; Multi-model ensemble; Pakistan; Taylor skill score; Temperature and precipitation |
学科领域 | Learning systems; Machine learning; Nearest neighbor search; Neural networks; Support vector machines; Coupled Model Intercomparison Project; General circulation model; K nearest neighbours (k-NN); Multi-model ensemble; Optimum performance; Pakistan; Relevance Vector Machine; Skill Score; Learning algorithms; air temperature; algorithm; climate modeling; climate prediction; ensemble forecasting; general circulation model; machine learning; precipitation assessment; Pakistan |
语种 | 英语 |
scopus关键词 | Learning systems; Machine learning; Nearest neighbor search; Neural networks; Support vector machines; Coupled Model Intercomparison Project; General circulation model; K nearest neighbours (k-NN); Multi-model ensemble; Optimum performance; Pakistan; Relevance Vector Machine; Skill Score; Learning algorithms; air temperature; algorithm; climate modeling; climate prediction; ensemble forecasting; general circulation model; machine learning; precipitation assessment; Pakistan |
来源期刊 | Atmospheric Research |
文献类型 | 期刊论文 |
条目标识符 | http://gcip.llas.ac.cn/handle/2XKMVOVA/120477 |
作者单位 | School of Civil Engineering, Universiti Teknologi Malaysia (UTM), Johor Bahru, 81310, Malaysia; Faculty of Engineering Sciences & Technology, Lasbela University of Agriculture, Water and Marine SciencesBalochistan, Pakistan; Institute for Sustainability and Innovation, College of Engineering and Science, Victoria University, P.O. Box 14428, Melbourne, Victoria 8001, Australia |
推荐引用方式 GB/T 7714 | Ahmed K.,Sachindra D.A.,Shahid S.,et al. Multi-model ensemble predictions of precipitation and temperature using machine learning algorithms[J],2020,236. |
APA | Ahmed K.,Sachindra D.A.,Shahid S.,Iqbal Z.,Nawaz N.,&Khan N..(2020).Multi-model ensemble predictions of precipitation and temperature using machine learning algorithms.Atmospheric Research,236. |
MLA | Ahmed K.,et al."Multi-model ensemble predictions of precipitation and temperature using machine learning algorithms".Atmospheric Research 236(2020). |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。