DOI: 10.1016/j.atmosres.2017.10.009
Scopus记录号: 2-s2.0-85033485125
论文题名: Research and application of a novel hybrid decomposition-ensemble learning paradigm with error correction for daily PM10 forecasting
作者: Luo H. ; Wang D. ; Yue C. ; Liu Y. ; Guo H.
刊名: Atmospheric Research
ISSN: 1698095
出版年: 2018
卷: 201 起始页码: 34
结束页码: 45
语种: 英语
英文关键词: Cuckoo search
; Daily PM10 forecasting
; Error correction
; Extreme learning machine
; Fast ensemble empirical mode decomposition
; Variational mode decomposition
Scopus关键词: Error correction
; Forecasting
; Knowledge acquisition
; Learning systems
; Machine components
; Optimization
; Cuckoo searches
; Ensemble empirical mode decomposition
; Error correction models
; Extreme learning machine
; Forecasting modeling
; Learning paradigms
; Mode decomposition
; Research and application
; Errors
; accuracy assessment
; algorithm
; concentration (composition)
; decomposition analysis
; ensemble forecasting
; error correction
; machine learning
; particulate matter
; Beijing [China]
; China
; Harbin
; Heilongjiang
英文摘要: In this paper, a hybrid decomposition-ensemble learning paradigm combining error correction is proposed for improving the forecast accuracy of daily PM10 concentration. The proposed learning paradigm is consisted of the following two sub-models: (1) PM10 concentration forecasting model; (2) error correction model. In the proposed model, fast ensemble empirical mode decomposition (FEEMD) and variational mode decomposition (VMD) are applied to disassemble original PM10 concentration series and error sequence, respectively. The extreme learning machine (ELM) model optimized by cuckoo search (CS) algorithm is utilized to forecast the components generated by FEEMD and VMD. In order to prove the effectiveness and accuracy of the proposed model, two real-world PM10 concentration series respectively collected from Beijing and Harbin located in China are adopted to conduct the empirical study. The results show that the proposed model performs remarkably better than all other considered models without error correction, which indicates the superior performance of the proposed model. © 2017 Elsevier B.V. Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/108988
Appears in Collections: 影响、适应和脆弱性 气候变化事实与影响
There are no files associated with this item.
作者单位: School of Economics and Management, China University of Geosciences, Wuhan, 430074, China; Mineral Resource Strategy and Policy Research Center, China University of Geosciences, Wuhan, 430074, China
Recommended Citation:
Luo H.,Wang D.,Yue C.,et al. Research and application of a novel hybrid decomposition-ensemble learning paradigm with error correction for daily PM10 forecasting[J]. Atmospheric Research,2018-01-01,201