气候变化领域集成服务门户(CCPortal): Improving the estimation of alpine grassland fractional vegetation cover using optimized algorithms and multi-dimensional features

CCPortal

DOI	10.1186/s13007-021-00796-5
	Improving the estimation of alpine grassland fractional vegetation cover using optimized algorithms and multi-dimensional features
	Lin, Xingchen; Chen, Jianjun; Lou, Peiqing; Yi, Shuhua; Qin, Yu; You, Haotian; Han, Xiaowen
通讯作者	Chen, JJ (通讯作者)，Guilin Univ Technol, Coll Geomat & Geoinformat, 12 Jiangan St, Guilin 541006, Peoples R China. ; Chen, JJ (通讯作者)，Guilin Univ Technol, Guangxi Key Lab Spatial Informat & Geomat, 12 Jiangan Rd, Guilin 541004, Peoples R China.
发表日期	2021
EISSN	1746-4811
卷号	17 期号:1
英文摘要	Background Fractional vegetation cover (FVC) is an important basic parameter for the quantitative monitoring of the alpine grassland ecosystem on the Qinghai-Tibetan Plateau. Based on unmanned aerial vehicle (UAV) acquisition of measured data and matching it with satellite remote sensing images at the pixel scale, the proper selection of driving data and inversion algorithms can be determined and is crucial for generating high-precision alpine grassland FVC products. Methods This study presents estimations of alpine grassland FVC using optimized algorithms and multi-dimensional features. The multi-dimensional feature set (using original spectral bands, 22 vegetation indices, and topographical factors) was constructed from many sources of information, then the optimal feature subset was determined based on different feature selection algorithms as the driving data for optimized machine learning algorithms. Finally, the inversion accuracy, sensitivity to sample size, and computational efficiency of the four machine learning algorithms were evaluated. Results (1) The random forest (RF) algorithm (R-2: 0.861, RMSE: 9.5%) performed the best for FVC inversion among the four machine learning algorithms driven by the four typical vegetation indices. (2) Compared with the four typical vegetation indices, using multi-dimensional feature sets as driving data obviously improved the FVC inversion accuracy of the four machine learning algorithms (R-2 of the RF algorithm increased to 0.890). (3) Among the three variable selection algorithms (Boruta, sequential forward selection [SFS], and permutation importance-recursive feature elimination [PI-RFE]), the constructed PI-RFE feature selection algorithm had the best dimensionality reduction effect on the multi-dimensional feature set. (4) The hyper-parameter optimization of the machine learning algorithms and feature selection of the multi-dimensional feature set further improved FVC inversion accuracy (R-2: 0.917 and RMSE: 7.9% in the optimized RF algorithm). Conclusion This study provides a highly precise, optimized algorithm with an optimal multi-dimensional feature set for FVC inversion, which is vital for the quantitative monitoring of the ecological environment of alpine grassland.
关键词	QINGHAI-TIBET PLATEAU LEAF-AREA INDEX GLOBAL VEGETATION FEATURE-SELECTION YELLOW-RIVER BARE SOIL LANDSAT 8 REMOTE REGRESSION RESOLUTION
英文关键词	Fractional vegetation cover (FVC); Alpine grassland; Unmanned aerial vehicle (UAV) aerial imagery; Machine learning algorithms; Feature selection; Parameter tuning; Accuracy evaluation
语种	英语
WOS研究方向	Biochemistry & Molecular Biology ; Plant Sciences
WOS类目	Biochemical Research Methods ; Plant Sciences
WOS记录号	WOS:000696819600001
来源期刊	PLANT METHODS
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/254758
作者单位	[Lin, Xingchen; Chen, Jianjun; You, Haotian; Han, Xiaowen] Guilin Univ Technol, Coll Geomat & Geoinformat, 12 Jiangan St, Guilin 541006, Peoples R China; [Chen, Jianjun; You, Haotian; Han, Xiaowen] Guilin Univ Technol, Guangxi Key Lab Spatial Informat & Geomat, 12 Jiangan Rd, Guilin 541004, Peoples R China; [Yi, Shuhua] Nantong Univ, Inst Fragile Ecosyst & Environm, 999 Tongjing Rd, Nantong 226007, Peoples R China; [Lou, Peiqing; Qin, Yu] Chinese Acad Sci, Northwest Inst Ecoenvironm & Resources, State Key Lab Cryospher Sci, 320 Donggang West Rd, Lanzhou 730000, Peoples R China
推荐引用方式 GB/T 7714	Lin, Xingchen,Chen, Jianjun,Lou, Peiqing,et al. Improving the estimation of alpine grassland fractional vegetation cover using optimized algorithms and multi-dimensional features[J]. 中国科学院西北生态环境资源研究院,2021,17(1).
APA	Lin, Xingchen.,Chen, Jianjun.,Lou, Peiqing.,Yi, Shuhua.,Qin, Yu.,...&Han, Xiaowen.(2021).Improving the estimation of alpine grassland fractional vegetation cover using optimized algorithms and multi-dimensional features.PLANT METHODS,17(1).
MLA	Lin, Xingchen,et al."Improving the estimation of alpine grassland fractional vegetation cover using optimized algorithms and multi-dimensional features".PLANT METHODS 17.1(2021).