干旱区生态环境知识资源中心(Arid): Estimating catchment scale soil moisture at a high spatial resolution: Integrating remote sensing and machine learning

Arid

DOI	10.1016/j.scitotenv.2021.145924
	Estimating catchment scale soil moisture at a high spatial resolution: Integrating remote sensing and machine learning
	Senanayake, I. P.; Yeo, I. -Y.; Walker, J. P.; Willgoose, G. R.
通讯作者	Senanayake, IP ; Yeo, IY (corresponding author), Univ Newcastle, Coll Engn Sci & Environm, Sch Engn, Callaghan, NSW 2308, Australia.
来源期刊	SCIENCE OF THE TOTAL ENVIRONMENT
ISSN	0048-9697
EISSN	1879-1026
出版年	2021
卷号	776
英文摘要	Soil moisture information is important for a wide range of applications including hydrologic modelling, climatic modelling and agriculture. L-band passivemicrowave satellite remote sensing is themost feasible option to estimate near-surface soil moisture (similar to 0-5 cmsoil depth) over large extents, but its coarse resolution (similar to 10s of km) means that it is unable to capture the variability of soil moisture in detail. Therefore, different downscaling methods have been tested as a solution tomeet the demand for high spatial resolution soil moisture. Downscaling algorithms based on the soil thermal inertia relationship between diurnal soil temperature difference (Delta T) and dailymean soil moisture content (mu(SM)) have shown promising results over arid and semi-arid landscapes. However, the linearity of these algorithms is affected by factors such as vegetation, soil texture and meteorology in a complex manner. This study tested a (i) Regression Tree (RT), an Artificial Neural Network (ANN), and a Gaussian Process Regression (GPR) model based on the soil thermal inertia theory over a semi-arid agricultural landscape in Australia, given the ability of machine learning algorithms to capture complex, non-linear relationships between predictors and responses. Downscaled soil moisture from the RT, ANN and GPR models showed root mean square errors (RMSEs) of 0.03, 0.09 and 0.07 cm(3)/cm(3) compared to airborne retrievals and unbiased RMSEs (ubRMSEs) of 0.07, 0.08 and 0.05 cm(3)/cm(3) compared to in-situ observations, respectively. The study showed encouraging results to integrate machine learning techniques in estimating near-surface soil moisture at a high spatial resolution. (c) 2021 Elsevier B.V. All rights reserved.
英文关键词	Artificial neural network Downscaling Gaussian process regression Regression tree model Soil moisture
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000647601200005
WOS关键词	GAUSSIAN PROCESS REGRESSION ; LAND-SURFACE TEMPERATURE ; THERMAL INERTIA ; DOWNSCALING APPROACH ; WATER CONTENT ; SMOS ; RETRIEVAL ; PRODUCTS ; MODEL ; VALIDATION
WOS类目	Environmental Sciences
WOS研究方向	Environmental Sciences & Ecology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/351657
作者单位	[Senanayake, I. P.; Yeo, I. -Y.; Willgoose, G. R.] Univ Newcastle, Coll Engn Sci & Environm, Sch Engn, Callaghan, NSW 2308, Australia; [Walker, J. P.] Monash Univ, Dept Civil Engn, Clayton, Vic 3800, Australia
推荐引用方式 GB/T 7714	Senanayake, I. P.,Yeo, I. -Y.,Walker, J. P.,et al. Estimating catchment scale soil moisture at a high spatial resolution: Integrating remote sensing and machine learning[J],2021,776.
APA	Senanayake, I. P.,Yeo, I. -Y.,Walker, J. P.,&Willgoose, G. R..(2021).Estimating catchment scale soil moisture at a high spatial resolution: Integrating remote sensing and machine learning.SCIENCE OF THE TOTAL ENVIRONMENT,776.
MLA	Senanayake, I. P.,et al."Estimating catchment scale soil moisture at a high spatial resolution: Integrating remote sensing and machine learning".SCIENCE OF THE TOTAL ENVIRONMENT 776(2021).