Modeling PM2.5 forecast using a self-weighted ensemble GRU network: Method optimization and evaluation

doi:10.1016/j.ecolind.2023.111138

	Modeling PM2.5 forecast using a self-weighted ensemble GRU network: Method optimization and evaluation
	Huang, Hengjun1,2 ; Qian, Chonghui 1,2
	2023-12-01
发表期刊	ECOLOGICAL INDICATORS
卷号	156
摘要	Due to the rapid industrial development and global concern about air pollution, understanding the dynamics of PM2.5 concentration has become a key aspect of air quality prediction. Many deep learning and mode decomposition techniques have been explored to capture the temporal and nonlinear features of PM2.5 concentration data. However, most of the existing methods ignore the differences in prediction losses of individual subsequences, resulting in lower prediction accuracy. To address this limitation, we proposed an ensemble gated recurrent unit (GRU) model that incorporated a self-weighted total loss function based on variational mode decomposition (VMD). In this approach, the PM2.5 concentration series were decomposed using the VMD, and then each decomposed subsequence (including the residual sequence) was fed into the GRU and the predicted loss of the subsequence was then calculated. For the model to output optimal predictions, we used a selfweighted ensemble loss function to adaptively optimize the prediction loss for each subsequence. Specifically, larger weights were assigned to the model's subsequences with higher predictive losses to better focus on those with higher predictive losses. In addition, the hyperparameter of the model was adjusted to adapt to various datasets in different domains. Experimental results on the three datasets show that our model performs better than the VMD-GRU and single GRU models. This validates the effectiveness of our model. Our approach has the advantage of plug-and-play, making it easier to seamlessly integrate deep learning techniques and pattern decomposition methods into air quality prediction.
关键词	PM2.5 forecasting Variational mode decomposition Self-weighted ensemble loss function Gated recurrent unit
DOI	10.1016/j.ecolind.2023.111138
收录类别	SCIE ; EI
ISSN	1470-160X
语种	英语
WOS研究方向	Biodiversity & Conservation ; Environmental Sciences & Ecology
WOS类目	Biodiversity Conservation ; Environmental Sciences
WOS记录号	WOS:001108837300001
出版者	ELSEVIER
EI入藏号	20234515023976
EI主题词	Variational mode decomposition
EI分类号	451.2 Air Pollution Control ; 461.4 Ergonomics and Human Factors Engineering ; 716.1 Information Theory and Signal Processing
原始文献类型	Article
EISSN	1872-7034
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.lzufe.edu.cn/handle/39EH0E1M/35474
专题	统计与数据科学学院
通讯作者	Huang, Hengjun
作者单位	1.Lanzhou Univ Finance & Econ, Sch Stat, Lanzhou 730020, Peoples R China; 2.Key Lab Digital Econ & Social Comp Sci Gansu, Lanzhou 730020, Peoples R China
第一作者单位	兰州财经大学
通讯作者单位	兰州财经大学
推荐引用方式 GB/T 7714	Huang, Hengjun,Qian, Chonghui. Modeling PM2.5 forecast using a self-weighted ensemble GRU network: Method optimization and evaluation[J]. ECOLOGICAL INDICATORS,2023,156.
APA	Huang, Hengjun,&Qian, Chonghui.(2023).Modeling PM2.5 forecast using a self-weighted ensemble GRU network: Method optimization and evaluation.ECOLOGICAL INDICATORS,156.
MLA	Huang, Hengjun,et al."Modeling PM2.5 forecast using a self-weighted ensemble GRU network: Method optimization and evaluation".ECOLOGICAL INDICATORS 156(2023).