干旱区生态环境知识资源中心(Arid): Towards a remote sensing data based evapotranspiration estimation in Northern Australia using a simple random forest approach

Arid

DOI	10.1016/j.jaridenv.2021.104513
	Towards a remote sensing data based evapotranspiration estimation in Northern Australia using a simple random forest approach
	Douna, V; Barraza, V; Grings, F.; Huete, A.; Restrepo-Coupe, N.; Beringer, J.
通讯作者	Douna, V (corresponding author), UBA CONICET, Inst Astron & Fis Espacio IAFE, Ciudad Univ, Buenos Aires, DF, Argentina.
来源期刊	JOURNAL OF ARID ENVIRONMENTS
ISSN	0140-1963
EISSN	1095-922X
出版年	2021
卷号	191
英文摘要	In this work we have developed a random forest regressor to predict daily evapotranspiration in three eddycovariance sites in Northern Australia from in-situ meteorological data and fluxes, and satellite leaf area index and land surface temperature data. The variable analysis for the random forest regressor suggests that leaf area index is the most important one at this temporal scale. A development sample corresponding to the period 2010-2013 was used, while the year 2014 has been separated for testing. Using this approach, we have obtained satisfactory performances in the three sites, with RMSE errors around 1 mm/day (and relative RMSEs similar to 0.3) in comparison to the measured values. With the final aim of testing the predictive capability of a model that uses remote sensing data as input, regressors that predict evapotranspiration exclusively from leaf area index and land surface temperature, have been trained resulting in reasonable performances. The RMSEs over the test set are similar to 1.1 - 1.2 mm/day. In all cases, the errors are comparable to those obtained in previous works that use similar locations and different methods. When compared to the measured values, the random forest predictions of evapotranspiration are more accurate than the global MODIS ET 8-day 1 km product, which was used as benchmark for the performance evaluation of our models, in the three selected locations.
英文关键词	Evapotranspiration Remote sensing Random forest Australia
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000660573200002
WOS关键词	LATENT-HEAT FLUX ; LAND-SURFACE TEMPERATURE ; UPSCALING EVAPOTRANSPIRATION ; SPATIAL VARIABILITY ; SAVANNA VEGETATION ; BIOMASS ESTIMATION ; ARID AREA ; WATER ; SATELLITE ; MODIS
WOS类目	Ecology ; Environmental Sciences
WOS研究方向	Environmental Sciences & Ecology
来源机构	University of Arizona ; University of Western Australia
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/350714
作者单位	[Douna, V; Barraza, V; Grings, F.] UBA CONICET, Inst Astron & Fis Espacio IAFE, Ciudad Univ, Buenos Aires, DF, Argentina; [Huete, A.; Restrepo-Coupe, N.] Univ Technol Sydney, Sch Life Sci, Sydney, NSW, Australia; [Restrepo-Coupe, N.] Univ Arizona, Dept Ecol & Evolutionary Biol, Tucson, AZ USA; [Beringer, J.] Univ Western Australia, Sch Agr & Environm, Crawley, WA, Australia
推荐引用方式 GB/T 7714	Douna, V,Barraza, V,Grings, F.,et al. Towards a remote sensing data based evapotranspiration estimation in Northern Australia using a simple random forest approach[J]. University of Arizona, University of Western Australia,2021,191.
APA	Douna, V,Barraza, V,Grings, F.,Huete, A.,Restrepo-Coupe, N.,&Beringer, J..(2021).Towards a remote sensing data based evapotranspiration estimation in Northern Australia using a simple random forest approach.JOURNAL OF ARID ENVIRONMENTS,191.
MLA	Douna, V,et al."Towards a remote sensing data based evapotranspiration estimation in Northern Australia using a simple random forest approach".JOURNAL OF ARID ENVIRONMENTS 191(2021).