干旱区生态环境知识资源中心(Arid): A framework for estimating actual evapotranspiration at weather stations without flux observations by combining data from MODIS and flux towers through a machine learning approach

Arid

DOI	10.1016/j.jhydrol.2021.127047
	A framework for estimating actual evapotranspiration at weather stations without flux observations by combining data from MODIS and flux towers through a machine learning approach
	Zhang, Chen; Luo, Geping; Hellwich, Olaf; Chen, Chunbo; Zhang, Wenqiang; Xie, Mingjuan; He, Huili; Shi, Haiyang; Wang, Yuangang
通讯作者	Luo, GP (corresponding author), Chinese Acad Sci, Xinjiang Inst Ecol & Geog, State Key Lab Desert & Oasis Ecol, Urumqi 830011, Peoples R China.
来源期刊	JOURNAL OF HYDROLOGY
ISSN	0022-1694
EISSN	1879-2707
出版年	2021
卷号	603
英文摘要	The scarcity of site-scale actual evapotranspiration (ET) measurements poses a challenge for modelling and verifying regional ET. Taking the grassland ecosystem in arid and semi-arid regions of Northern China (ASNC) as an example, we proposed a framework for estimating ET at weather stations without flux observations through a machine learning approach by combining data from MODIS and fifteen flux towers distributed in alpine grassland (AG) and temperate grassland (TG) across ASNC. First, we analyzed the temporal characteristics of grassland ET at site scale. Second, we applied the machine learning approach Random Forest (RF) to develop a robust model for simulating site-scale grassland ET, and used random and spatial cross-validations (CVs) and three metrics to evaluate the RF models performance. Two strategies (using pooled data from all flux towers for a general model, and dividing data by grassland type to develop models specific to AG and TG) and four temporal resolutions (daily, 8-day, monthly and seasonal) were used to develop the RF models. Third, we investigated how the importance of predictor variables for estimating grassland ET changed in different CVs, strategies and temporal resolutions. The ET of AG and TG showed similar dynamic patterns but differed in magnitude. The RF models showed good performance in both strategies and all four temporal resolutions (R-2 > 0.64, MAE < 0.53 mm d(-1), RMSE < 0.72 mm d(-1)). However, seasonal ET simulations performed better than that of daily, 8-day and monthly using pooled data from all flux towers, especially in spatial CV. Meteorological variables (temperature, precipitation and radiation), vegetation (NDVI, LAI and FPAR) and soil (soil water content and soil temperature) were strong predictors of variation in grassland ET. Changes in the importance ranking and value of predictor variables partly explained the variations of model performance. The robust model performance in spatial CV proved that the framework developed in this study was reliable when applied to weather stations without flux observations, thereby overcoming the scarcity of site-scale actual ET measurements.
英文关键词	Evapotranspiration Weather stations without flux observations Multiple temporal resolutions Spatial cross-validation Machine learning Grasslands
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000711024300020
WOS关键词	GROSS PRIMARY PRODUCTION ; ENERGY-BALANCE CLOSURE ; NET ECOSYSTEM EXCHANGE ; WATER-USE EFFICIENCY ; EDDY-COVARIANCE ; GRASSLAND ECOSYSTEMS ; CARBON-DIOXIDE ; AMERIFLUX DATA ; TERRESTRIAL EVAPOTRANSPIRATION ; CONTRASTING RESPONSES
WOS类目	Engineering, Civil ; Geosciences, Multidisciplinary ; Water Resources
WOS研究方向	Engineering ; Geology ; Water Resources
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/374041
作者单位	[Zhang, Chen; Luo, Geping; Chen, Chunbo; Zhang, Wenqiang; Xie, Mingjuan; He, Huili; Shi, Haiyang; Wang, Yuangang] Chinese Acad Sci, Xinjiang Inst Ecol & Geog, State Key Lab Desert & Oasis Ecol, Urumqi 830011, Peoples R China; [Zhang, Chen; Luo, Geping; Chen, Chunbo; Zhang, Wenqiang; Xie, Mingjuan; He, Huili; Shi, Haiyang; Wang, Yuangang] Univ Chinese Acad Sci, Beijing 100049, Peoples R China; [Luo, Geping] Chinese Acad Sci, Res Ctr Ecol & Environm Cent Asia, Urumqi 830011, Peoples R China; [Hellwich, Olaf] Tech Univ Berlin, Dept Comp Vis & Remote Sensing, D-10587 Berlin, Germany; [Zhang, Wenqiang; Xie, Mingjuan; He, Huili; Shi, Haiyang] Univ Ghent, Dept Geog, B-9000 Ghent, Belgium; [Zhang, Wenqiang; Xie, Mingjuan; He, Huili; Shi, Haiyang] Sino Belgian Joint Lab Geoinformat, B-9000 Ghent, Belgium; [Zhang, Wenqiang; Xie, Mingjuan; He, Huili; Shi, Haiyang] Sino Belgian Joint Lab Geoinformat, Urumqi 830011, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Chen,Luo, Geping,Hellwich, Olaf,et al. A framework for estimating actual evapotranspiration at weather stations without flux observations by combining data from MODIS and flux towers through a machine learning approach[J],2021,603.
APA	Zhang, Chen.,Luo, Geping.,Hellwich, Olaf.,Chen, Chunbo.,Zhang, Wenqiang.,...&Wang, Yuangang.(2021).A framework for estimating actual evapotranspiration at weather stations without flux observations by combining data from MODIS and flux towers through a machine learning approach.JOURNAL OF HYDROLOGY,603.
MLA	Zhang, Chen,et al."A framework for estimating actual evapotranspiration at weather stations without flux observations by combining data from MODIS and flux towers through a machine learning approach".JOURNAL OF HYDROLOGY 603(2021).