气候变化领域集成服务门户(CCPortal): Corn Biomass Estimation by Integrating Remote Sensing and Long-Term Observation Data Based on Machine Learning Techniques

CCPortal

DOI	10.3390/rs13122352
	Corn Biomass Estimation by Integrating Remote Sensing and Long-Term Observation Data Based on Machine Learning Techniques
	Geng, Liying; Che, Tao; Ma, Mingguo; Tan, Junlei; Wang, Haibo
发表日期	2021
EISSN	2072-4292
卷号	13 期号:12
英文摘要	The accurate and timely estimation of regional crop biomass at different growth stages is of great importance in guiding crop management decision making. The recent availability of long time series of remote sensing data offers opportunities for crop monitoring. In this paper, four machine learning models, namely random forest (RF), support vector machine (SVM), artificial neural network (ANN), and extreme gradient boosting (XGBoost) were adopted to estimate the seasonal corn biomass based on field observation data and moderate resolution imaging spectroradiometer (MODIS) reflectance data from 2012 to 2019 in the middle reaches of the Heihe River basin, China. Nine variables were selected with the forward feature selection approach from among twenty-seven variables potentially influencing corn biomass: soil-adjusted total vegetation index (SATVI), green ratio vegetation index (GRVI), Nadir_B7 (2105-2155 nm), Nadir_B6 (1628-1652 nm), land surface water index (LSWI), normalized difference vegetation index (NDVI), Nadir_B4 (545-565 nm), and Nadir_B3 (459-479 nm). The results indicated that the corn biomass was suitably estimated (the coefficient of determination (R-2) was between 0.72 and 0.78) with the four machine learning models. The XGBoost model performed better than the other three models (R-2 = 0.78, root mean squared error (RMSE) = 2.86 t/ha and mean absolute error (MAE) = 1.86 t/ha). Moreover, the RF model was an effective method (R-2 = 0.77, RMSE = 2.91 t/ha and MAE = 1.91 t/ha), with a performance comparable to that of the XGBoost model. This study provides a reference for estimating crop biomass from MOD43A4 datasets. In addition, the research demonstrates the potential of machine learning techniques to achieve a relatively accurate estimation of daily corn biomass at a large scale.
英文关键词	corn; biomass; field data; MODIS; machine learning models
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
WOS关键词	UNMANNED AERIAL VEHICLE ; LEAF-AREA INDEX ; ABOVEGROUND BIOMASS ; VEGETATION INDEX ; RANDOM FOREST ; SPECTRAL REFLECTANCE ; CHLOROPHYLL CONTENT ; YIELD ESTIMATION ; NEURAL-NETWORKS ; NITROGEN STATUS
WOS记录号	WOS:000666482100001
来源期刊	REMOTE SENSING
来源机构	中国科学院西北生态环境资源研究院
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/241024
作者单位	[Geng, Liying; Che, Tao; Tan, Junlei; Wang, Haibo] Chinese Acad Sci, Northwest Inst Ecoenvironm & Resources, Key Lab Remote Sensing Gansu Prov, Heihe Remote Sensing Expt Res Stn, Lanzhou 730000, Peoples R China; [Che, Tao] Chinese Acad Sci, Ctr Excellence Tibetan Plateau Earth Sci, Beijing 100101, Peoples R China; [Ma, Mingguo] Southwest Univ, Sch Geog Sci, Chongqing Jinfo Mt Karst Ecosyst Natl Observat &, Chongqing 400715, Peoples R China
推荐引用方式 GB/T 7714	Geng, Liying,Che, Tao,Ma, Mingguo,et al. Corn Biomass Estimation by Integrating Remote Sensing and Long-Term Observation Data Based on Machine Learning Techniques[J]. 中国科学院西北生态环境资源研究院,2021,13(12).
APA	Geng, Liying,Che, Tao,Ma, Mingguo,Tan, Junlei,&Wang, Haibo.(2021).Corn Biomass Estimation by Integrating Remote Sensing and Long-Term Observation Data Based on Machine Learning Techniques.REMOTE SENSING,13(12).
MLA	Geng, Liying,et al."Corn Biomass Estimation by Integrating Remote Sensing and Long-Term Observation Data Based on Machine Learning Techniques".REMOTE SENSING 13.12(2021).