干旱区生态环境知识资源中心(Arid): Evaluation of water flux predictive models developed using eddy-covariance observations and machine learning: a meta-analysis

Arid

DOI	10.5194/hess-26-4603-2022
	Evaluation of water flux predictive models developed using eddy-covariance observations and machine learning: a meta-analysis
	Shi, Haiyang; Luo, Geping; Hellwich, Olaf; Xie, Mingjuan; Zhang, Chen; Zhang, Yu; Wang, Yuangang; Yuan, Xiuliang; Ma, Xiaofei; Zhang, Wenqiang; Kurban, Alishir; De Maeyer, Philippe; Van de Voorde, Tim
通讯作者	Luo, GP
来源期刊	HYDROLOGY AND EARTH SYSTEM SCIENCES
ISSN	1027-5606
EISSN	1607-7938
出版年	2022
卷号	26 期号:18 页码:4603-4618
英文摘要	With the rapid accumulation of water flux observations from global eddy-covariance flux sites, many studies have used data-driven approaches to model water fluxes, with various predictors and machine learning algorithms used. However, it is unclear how various model features affect prediction accuracy. To fill this gap, we evaluated this issue based on records of 139 developed models collected from 32 such studies. Support vector machines (SVMs; average R-squared = 0.82) and RF (random forest; average R-squared = 0.81) outperformed other evaluated algorithms with sufficient sample size in both cross-study and intra-study (with the same data) comparisons. The average accuracy of the model applied to arid regions is higher than in other climate types. The average accuracy of the model was slightly lower for forest sites (average R-squared = 0.76) than for croplands and grasslands (average R -squared = 0.8 and 0.79) but higher than for shrubland sites (average R-squared = 0.67). Using R-n/ R-s, precipitation, T-a, and the fraction of absorbed photosynthetically active radiation (FA-PAR) improved the model accuracy. The combined use of T-a and R-n/ R-s is very effective, especially in forests, while in grasslands the combination of W-s and R-n/ R-s is also fective. Random cross-validation showed higher model accuracy than spatial cross-validation and temporal cross-validation, but spatial cross-validation is more important in spatial extrapolation. The findings of this study are promising to guide future research on such machine-learning-based modeling.
类型	Article
语种	英语
开放获取类型	Green Published, gold
收录类别	SCI-E
WOS记录号	WOS:000854100800001
WOS关键词	GLOBAL TERRESTRIAL EVAPOTRANSPIRATION ; CARBON ; MODIS ; UNCERTAINTY ; ECOSYSTEMS ; RESPONSES ; TOWERS ; BUDGET ; CO2
WOS类目	Geosciences, Multidisciplinary ; Water Resources
WOS研究方向	Geology ; Water Resources
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/393060
推荐引用方式 GB/T 7714	Shi, Haiyang,Luo, Geping,Hellwich, Olaf,et al. Evaluation of water flux predictive models developed using eddy-covariance observations and machine learning: a meta-analysis[J],2022,26(18):4603-4618.
APA	Shi, Haiyang.,Luo, Geping.,Hellwich, Olaf.,Xie, Mingjuan.,Zhang, Chen.,...&Van de Voorde, Tim.(2022).Evaluation of water flux predictive models developed using eddy-covariance observations and machine learning: a meta-analysis.HYDROLOGY AND EARTH SYSTEM SCIENCES,26(18),4603-4618.
MLA	Shi, Haiyang,et al."Evaluation of water flux predictive models developed using eddy-covariance observations and machine learning: a meta-analysis".HYDROLOGY AND EARTH SYSTEM SCIENCES 26.18(2022):4603-4618.