干旱区生态环境知识资源中心(Arid): Prediction of Soil Moisture Content by Selecting Spectral Characteristics Using Random Forest Method

Arid

DOI	10.3788/LOP55.113002
	Prediction of Soil Moisture Content by Selecting Spectral Characteristics Using Random Forest Method
	Bao Qingling; Ding Jianli; Wang Jingzhe
通讯作者	Ding, JL
来源期刊	LASER & OPTOELECTRONICS PROGRESS
ISSN	1006-4125
出版年	2018
卷号	55 期号:11
英文摘要	In order to more accurately analyze the importance of spectral absorption characteristic parameters, which in different soil moisture absorption bands in soil spectra, in soil moisture content estimation, we collect 38 soil samples in Ugan-Kuqa river oasis in Xinjiang to measure soil spectral reflectance and soil moisture content. The characteristic parameters of spectral water absorption arc extracted with the continuum-removal method, the features include the maximum absorption depth D, the absorption peak right area R-a, the absorption peak left arca L-a, the absorption peak total arca A, arca normalization maximum absorption depth D-Lambda, and symmetry S. With the correlation analysis of the features and soil moisture content, we use random forest method to classify the characteristic parameters of spectral water absorption, and obtain the importance of each parameter to soil moisture content. Multiple stepwise regression model is used to establish soil moisture content inversion model. The results arc as follows: D and A have the strongest correlation with the soil moisture content, the correlation between spectral absorption parameters in the band of 2200 nm or 1100 nm and SMC is better than that of 1900 nm band; the top five parameters that arc important for soil moisture content arc obtained, they arc D-2200, L-a2200, A(2200), D-1900 and R-a2200, respectively; the best prediction model of SMC is the multiple stepwise regression model with A(2200) and D-2200, the decision coefficient of the modelling set is 0.88, root mean square error of modeling set is 2.08, decision coefficient of the test set is 0.89, prediction root mean square error is 2.21, and the relative analysis error is 2.80. Random forest classification can obtain the important spectral water characteristic parameters which have great influence on soil moisture content, and it provides a new method for accurate and rapid estimation of soil moisture content in arid areas.
英文关键词	spectroscopy soil moisture content random forest absorption characteristic parameter
类型	Article
语种	中文
收录类别	ESCI
WOS记录号	WOS:000549825800058
WOS类目	Engineering, Electrical & Electronic ; Optics
WOS研究方向	Engineering ; Optics
Scopus学科分类	Xinjiang Univ, Key Lab Oasis Ecol, Minist Educ, Urumqi 830016, Xinjiang, Peoples R China.
来源机构	新疆大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/333383
作者单位	[Bao Qingling; Ding Jianli; Wang Jingzhe] Xinjiang Univ, Key Lab Wisdom City & Environm Modeling, Coll Resource & Environm Sci, Urumqi 830016, Xinjiang, Peoples R China; [Bao Qingling; Ding Jianli; Wang Jingzhe] Xinjiang Univ, Key Lab Oasis Ecol, Minist Educ, Urumqi 830016, Xinjiang, Peoples R China
推荐引用方式 GB/T 7714	Bao Qingling,Ding Jianli,Wang Jingzhe. Prediction of Soil Moisture Content by Selecting Spectral Characteristics Using Random Forest Method[J]. 新疆大学,2018,55(11).
APA	Bao Qingling,Ding Jianli,&Wang Jingzhe.(2018).Prediction of Soil Moisture Content by Selecting Spectral Characteristics Using Random Forest Method.LASER & OPTOELECTRONICS PROGRESS,55(11).
MLA	Bao Qingling,et al."Prediction of Soil Moisture Content by Selecting Spectral Characteristics Using Random Forest Method".LASER & OPTOELECTRONICS PROGRESS 55.11(2018).