Predicting assemblages and species richness of endemic fish in the upper Yangtze River

CORC > 水生生物研究所 > 中科院水生所知识产出（2009年前） > 水生生物多样性与资源保护研究中心 > 期刊论文

	Predicting assemblages and species richness of endemic fish in the upper Yangtze River
	He, Yongfeng 1,2,3; Wang, Jianwei 1; Lek-Ang, Sithan 2; Lek, Sovan 2
刊名	SCIENCE OF THE TOTAL ENVIRONMENT
	2010-09-01
卷号	408 期号:19 页码:4211-4220
关键词	Endemic fish Species richness pattern Environmental variables Yangtze River CART RF
ISSN号	0048-9697
通讯作者	He, YF, Chinese Acad Sci, Inst Hydrobiol, 7 Donghu S Road, Wuhan 430072, Hubei, Peoples R China
中文摘要	The present work describes the ability of two modeling methods, Classification and Regression Tree (CART) and Random Forest (RF), to predict endemic fish assemblages and species richness in the upper Yangtze River, and then to identify the determinant environmental factors contributing to the models. The models included 24 predictor variables and 2 response variables (fish assemblage and species richness) for a total of 46 site units. The predictive quality of the modeling approaches was judged with a leave-one-out validation procedure. There was an average success of 60.9% and 71.7% to assign each site unit to the correct assemblage of fish, and 73% and 84% to explain the variance in species richness, by using CART and RF models, respectively. RF proved to be better than CART in terms of accuracy and efficiency in ecological applications. In any case, the mixed models including both land cover and river characteristic variables were more powerful than either individual one in explaining the endemic fish distribution pattern in the upper Yangtze River. For instance, altitude, slope, length, discharge, runoff, farmland and alpine and sub-alpine meadow played important roles in driving the observed endemic fish assemblage structure, while farmland, slope grassland, discharge, runoff, altitude and drainage area in explaining the observed patterns of endemic species richness. Therefore, the various effects of human activity on natural aquatic ecosystems, in particular, the flow modification of the river and the land use changes may have a considerable effect on the endemic fish distribution patterns on a regional scale. (C) 2010 Elsevier B.V. All rights reserved.
英文摘要	The present work describes the ability of two modeling methods, Classification and Regression Tree (CART) and Random Forest (RF), to predict endemic fish assemblages and species richness in the upper Yangtze River, and then to identify the determinant environmental factors contributing to the models. The models included 24 predictor variables and 2 response variables (fish assemblage and species richness) for a total of 46 site units. The predictive quality of the modeling approaches was judged with a leave-one-out validation procedure. There was an average success of 60.9% and 71.7% to assign each site unit to the correct assemblage of fish, and 73% and 84% to explain the variance in species richness, by using CART and RF models, respectively. RF proved to be better than CART in terms of accuracy and efficiency in ecological applications. In any case, the mixed models including both land cover and river characteristic variables were more powerful than either individual one in explaining the endemic fish distribution pattern in the upper Yangtze River. For instance, altitude, slope, length, discharge, runoff, farmland and alpine and sub-alpine meadow played important roles in driving the observed endemic fish assemblage structure, while farmland, slope grassland, discharge, runoff, altitude and drainage area in explaining the observed patterns of endemic species richness. Therefore, the various effects of human activity on natural aquatic ecosystems, in particular, the flow modification of the river and the land use changes may have a considerable effect on the endemic fish distribution patterns on a regional scale. (C) 2010 Elsevier B.V. All rights reserved.
学科主题	Environmental Sciences
WOS标题词	Science & Technology ; Life Sciences & Biomedicine
类目[WOS]	Environmental Sciences
研究领域[WOS]	Environmental Sciences & Ecology
关键词[WOS]	RANDOM FORESTS ; LAND-COVER ; LONGITUDINAL PATTERNS ; STREAM ECOSYSTEMS ; REGRESSION TREES ; CLASSIFICATION ; HABITAT ; ONTARIO ; FRANCE ; MODELS
收录类别	SCI
资助信息	Construction Committee of China [SX2007-019, SX2009-019]; Ministry of Water Resources of the People's Republic of China [200901011]; French embassy
语种	英语
WOS记录号	WOS:000280917300029
公开日期	2010-12-23
内容类型	期刊论文
源URL	[http://ir.ihb.ac.cn/handle/342005/13467]
专题	水生生物研究所_水生生物多样性与资源保护研究中心_期刊论文
作者单位	1.Chinese Acad Sci, Inst Hydrobiol, Wuhan 430072, Hubei, Peoples R China 2.Univ Toulouse, Lab Evolut & Divers Biol, CNRS, UMR 5174, F-31062 Toulouse 4, France 3.Chinese Acad Sci, Grad Univ, Beijing 100039, Peoples R China
推荐引用方式 GB/T 7714	He, Yongfeng,Wang, Jianwei,Lek-Ang, Sithan,et al. Predicting assemblages and species richness of endemic fish in the upper Yangtze River[J]. SCIENCE OF THE TOTAL ENVIRONMENT,2010,408(19):4211-4220.
APA	He, Yongfeng,Wang, Jianwei,Lek-Ang, Sithan,&Lek, Sovan.(2010).Predicting assemblages and species richness of endemic fish in the upper Yangtze River.SCIENCE OF THE TOTAL ENVIRONMENT,408(19),4211-4220.
MLA	He, Yongfeng,et al."Predicting assemblages and species richness of endemic fish in the upper Yangtze River".SCIENCE OF THE TOTAL ENVIRONMENT 408.19(2010):4211-4220.