气候变化领域集成服务门户(CCPortal): Hybrid deep learning method for a week-ahead evapotranspiration forecasting

CCPortal

DOI	10.1007/s00477-021-02078-x
	Hybrid deep learning method for a week-ahead evapotranspiration forecasting
	Ahmed, A. A. Masrur; Deo, Ravinesh C.; Feng, Qi; Ghahramani, Afshin; Raj, Nawin; Yin, Zhenliang; Yang, Linshan
发表日期	2021
ISSN	1436-3240
EISSN	1436-3259
英文摘要	Reference crop evapotranspiration (ETo) is an integral hydrological factor in soil-plant-atmospheric water balance studies and the management of drought events. This paper proposes a new hybrid-deep learning approach, combining convolutional neural network (CNN) and gated recurrent unit (GRU) along with Ant Colony Optimization (ACO), for a multi-step (week 1 to 4) daily-ETo forecast. The method also assimilates a comprehensive dataset with 52 diverse predictors, i.e., satellite-derived moderate resolution imaging spectroradiometer, ground-based datasets from scientific information for landowners and synoptic-scale climate indices. To develop a vigorous CNN-GRU model, a feature selection stage entails the ant colony optimization method implemented to improve the ETo forecast model for the three selected sites in Australian Murray Darling Basin. The results demonstrate excellent forecasting capability of the hybrid CNN-GRU model against the counterpart benchmark models, evidenced by a relatively small mean absolute error and high efficiency. Overall, this study shows that the proposed hybrid CNN-GRU model successfully apprehends the complex and non-linear relationships between predictor variables and the daily ETo.
英文关键词	Convolutional neural network; Gated recurrent unit; Hybrid-deep learning; ETo forecasting
WOS研究方向	Engineering ; Environmental Sciences & Ecology ; Mathematics ; Water Resources
WOS类目	Engineering, Environmental ; Engineering, Civil ; Environmental Sciences ; Statistics & Probability ; Water Resources
WOS关键词	ARTIFICIAL NEURAL-NETWORK ; EMPIRICAL MODE DECOMPOSITION ; SHORT-TERM-MEMORY ; CLIMATE INDEXES ; SYNOPTIC-SCALE ; PREDICTION ; ALGORITHM ; MACHINE ; PRECIPITATION ; OPTIMIZATION
WOS记录号	WOS:000693487400001
来源期刊	STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
来源机构	中国科学院西北生态环境资源研究院
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/239430
作者单位	[Ahmed, A. A. Masrur; Deo, Ravinesh C.; Raj, Nawin] Univ Southern Queensland, Sch Sci, Springfield, Qld 4300, Australia; [Feng, Qi; Yin, Zhenliang; Yang, Linshan] Chinese Acad Sci, Key Lab Ecohydrol Inland River Basin, Beijing, Peoples R China; [Feng, Qi; Yin, Zhenliang; Yang, Linshan] Chinese Acad Sci, Northwest Inst Ecoenvironm & Resources, Donggang West Rd 320, Lanzhou 730000, Gansu, Peoples R China; [Ghahramani, Afshin] Univ Southern Queensland, Ctr Sustainable Agr Syst, Springfield, Qld 4500, Australia
推荐引用方式 GB/T 7714	Ahmed, A. A. Masrur,Deo, Ravinesh C.,Feng, Qi,et al. Hybrid deep learning method for a week-ahead evapotranspiration forecasting[J]. 中国科学院西北生态环境资源研究院,2021.
APA	Ahmed, A. A. Masrur.,Deo, Ravinesh C..,Feng, Qi.,Ghahramani, Afshin.,Raj, Nawin.,...&Yang, Linshan.(2021).Hybrid deep learning method for a week-ahead evapotranspiration forecasting.STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT.
MLA	Ahmed, A. A. Masrur,et al."Hybrid deep learning method for a week-ahead evapotranspiration forecasting".STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT (2021).