随机森林算法在新疆物种丰富度影响因素研究中的应用

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (2206 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Taken gridded spatial distribution data of bird and mammal species of Xinjiang in 2010 as primary data source, combined with multi-sources of remote sensing data production, such as land use, vegetation, climate, and topographic data, determinants which affected birds and mammal species richness in Xinjiang have been recognized and their spatial variation was discussed. Importance of each determinant which affected the number of bird and mammal species have been assessed and ranked using Random Forest approach. Then relationship models between species richness and determinants were built through exploratory regression analysis. Three main habitats of grassland, woodland and farmland were taken out and the difference of effect factors to birds and mammals species richness between them were compared and analyzed. The results show that among all the determinants, vegetation growing status and their energy conversion capability were the most two important factors for bird richness. As for grassland habitat, the importance of altitude was 38.38%, which was highest value. Climate type in farmland had significant impacts on bird diversity, among which the importance of annual average temperature reaches 32.98%. Climate and altitude were very important considerations for mammal when choosing a habitat, accountied for more than 60% of the importance, and the highest was 76.85%. In cultivated land, climatic factors were more important than vegetation growth for mammalian habitat. Optimal models for birds and mammals under different types of habitats were varied and their variables were different accordingly. Model performance of farmland for birds and forest for mammals were the best two, which could explain the relationship between determinants and species richness about 69.9% and 68.9%, respectively. The results of both random forest and exploratory regression analysis shown that altitude, average annual temperature and precipitation were the most three important determinants to mammal species richness.

Key words： birds and mammals species richness determinants random forest exploratory regression

Received: 16 July 2020

PACS:

X176

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	LI Guang-yi
	LI Hai-ping
	WAN Hua-wei
	LI Li-ping

Cite this article:

LI Guang-yi,LI Hai-ping,WAN Hua-wei等. Research on determinants of species richness in xinjiang based on random forest appraoch[J]. CHINA ENVIRONMENTAL SCIENCECE, 2021, 41(2): 941-950.

URL:

http://www.zghjkx.com.cn/EN/ OR http://www.zghjkx.com.cn/EN/Y2021/V41/I2/941

[1]	万华伟,王永财,侯鹏,等.2001~2016年中国生物多样性保护优先区域植被和水域动态监测与分析[J]. 生态与农村环境学报, 2019, 5(3):273-282.Wan H W, Wang Y C, Hou P, et al. Monitoring and analysis on vegetation and waters dynamics in Chinese priority areas for biodiversity conservation during 2001~2016[J]. Journal of Ecology and Rural Environment, 2019,35(3):273-282.
[2]	马鸣.新疆鸟类名录[M]. 北京:科学出版社, 2001.Ma M. A Checklist of Birds in Xinjiang, China[M]. Beijing:Science Press, 2001.
[3]	阿布力米提·阿布都卡迪尔.新疆哺乳类(兽纲)名录[M]. 北京:科学出版社, 2002.Aptimi A. A Checklist of the mammals in Xinjiang, China[M]. Beijing:Science Press, 2002.
[4]	沙拉·哈纳皮亚,丁鹏,阴俊齐,等.中国新疆与哈萨克斯坦物种多样性特征及其保护现状[J]. 安徽农学通报, 2017,23(16):40-42.Sarah H, Ding P, Yin J Q, et al. The characteristics of species diversity and protection status in Xinjiang, China and Kazakhstan[J]. Anhui Agricultural Science Bulletin, 2017,23(16):40-42.
[5]	刘路平.山东省鸟类物种丰富度的地理格局及其与环境因子的关系[D]. 济南:山东师范大学, 2017.Liu L P. Geographic Patterns of avian species richness in Shandong Province and their environmental factors[D]. Jinan:Shandong Normal University, 2017.
[6]	刘澈,郑成洋,张腾,等.中国鸟类物种丰富度的地理格局及其与环境因子的关系[J]. 北京大学学报(自然科学版), 2014,50(3):29-38.Liu C, Zheng C Y, Zhang T, et al. Geographic patterns of avian species richness in China and their environmental factors[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2014,50(3):429-438.
[7]	田凯.鄂西北野生脊椎动物物种多样性及地理分布格局研究[D]. 武汉:湖北大学, 2017.Tian K. Reserch on species diversity and geographical distribution type of wild vertebrate in northwestern Hubei province, China[D]. Wuhan:Hubei University, 2017.
[8]	沈梦伟,毕孟杰,敬琴,等.中国两栖动物物种丰富度省级地理分布格局及其与气候因子的关系[J]. 四川动物, 2016,35(1):9-16.Shen M W, Bi M J, Jing Q, et al. Relationships between geographic amphibian species richiness provincial pattern and environmental factors om China[J]. Sichuan Jouenal of Zoology, 2016,35(1):9-16.
[9]	肖辉,郝元涛,徐晓,等.基于随机森林算法和Logistic回归模型的糖尿病风险因素研究[J]. 中国数字医学, 2018,13(1):33-35,40.Xiao H, Hao Y T, Xu X Y, et al. Study on risk factors of diabetes basd on random forest algorithm and logistic regression model[J]. China Digital Medicine, 2018,13(1):33-35,40.
[10]	Lopatin J, Dolos K, Hernandez H J, et al. Comparing Generalized Linear Models and random forest to model vascular plant species richness using LiDAR data in a natural forest in central Chile[J]. Remote Sensing of Environment An Interdisciplinary Journal, 2016.
[11]	李紫晶.蒙古高原草原与旱生灌丛生态系统生物多样性与生产力关系研究[D]. 呼和浩特:内蒙古大学, 2020.Li Z J. The relationships between biodiversity and productivity of grassland and xerophytic shrub ecosystems on the mongolian plateau[D]. Huhhot:Inner Mongolia University, 2020.
[12]	乌兰,姜晓东.新疆牦牛现状及发展前景[J]. 新疆畜牧业, 2016, 8):24-25.Wu L, Jiang X D. The current situation and development prospects of Xinjiang yak[J]. Xinjiang Xumuye, 2016,(8):24-25.
[13]	杨应川,陈立,郭东风,等.昆仑山地带野牦牛种群活动调查[J]. 安徽农业科学, 2014,42(15):4660-4661.Yang Y C, Chen L, Guo D F, et al. Investigation on population activity of wild yak in Kunlun Mountain Area[J]. Journal of Anhui Agricultural Sciences, 2014,42(15):4660-4661.
[14]	李克智.沙漠之舟——骆驼[J]. 野生动物, 1989,(2):49-50.Li K Z. The boat of desert camel[J]. Chinese Journal of Wildlife, 1989, 2):49-50.
[15]	Midgley G F, Hannah L, Millar D, et al.Developing regional and s pecies-level assessment of climat e ch ange impacts on biodiversity in the cape floristic region[J].Biological Con ser-vati on, 2003,112:87-7.
[16]	吴建国,周巧富.气候变化对6种荒漠动物分布的潜在影响[J]. 中国沙漠, 2011,31(2):464-475.Wu J G, Zhou Q F. Potential effect of climate change on distribution of 6desert animals in China[J]. Journal of Desert Research, 2011,31(2):464-475.
[17]	伍一宁,钟海秀,王继丰,等.气候变化对野生鸟类的影响研究进展[J]. 安徽农业科学, 2014,42(35):12549-12551.Wu Y N, Zhong H X, Wang J F, et al. Research Progress on the Impact of Climate Change on Wild Birds[J]. Journal of Anhui Agricultural Sciences, 2014,42(35):12549-12551.
[18]	龙昶宇,万华伟,李利平,等.新疆地区鸟类和哺乳动物丰富度与环境因子的空间格局与关系[J]. 遥感学报, 2019,23(1):155-165.Long C Y, Wan H W, Li L P, et al. Spatial patterns and correlations in the richness of bird and mammal species and environmental factors in Xinjiang, China[J]. Journal of Remote Sensing, 2019,23(1):155-165.
[19]	李利平,尹林克,唐志尧.新疆野生动植物物种丰富度的分布格局[J]. 干旱区研究, 2011,28(1):1-9.Li L P, Yin L K, Tang Z Y. Distribution Patterns of the Species Richness of Plants and Animals in Xinjiang, China[J]. Arid Zone Research, 2011,28(1):1-9.
[20]	许玉凤,杨井,陈亚宁,等.近32年来新疆地区植被覆盖的时空变化[J]. 草业科学, 2015,32(5):702.Xu Y F, Yang J, Chen Y N, et al. The spatial-temporal variations of vegetation cover in Xinjiang from 1982~2013[J]. Pratacultural Science, 2015,32(5):702.
[21]	Breiman L, Friedman J, Olshen R, et al. Classification and Regression Trees[J]. Chapman & Hall, 1984:1-359.
[22]	Breiman L. Statistical Modeling:The two cultures[J]. Statistical Science, 2011,16:199-215.
[23]	郭桂祯,刘乃山.基于随机森林模型的区域洪涝灾害房屋倒损评估方法研究[J]. 灾害学, 2018,33(3):48-51.Guo G Z, Liu N S. A method research of house damage assessment based on random forest model for regional flood disaster[J]. Journal of catastrophology, 2018,33(3):48-51.
[24]	Cybenko G. Approximation by super positions of a sigmoidal function[J]. Mathematics of Control, Signals, and Systems, 1989,2(4):303-14.
[25]	杨尚梅,陈颖,吉守祥.基于红外光谱和随机森林的蕨麻产地鉴别[J]. 实验室研究与探索, 2017,36(3):13-15,19.Yang S M, Chen Y, Ji S X. Identifying the Origin of Potentilla Anserine Based on Infrared Spectroscopy and Random Forest Method[J]. Research and Exploration in Laboratory, 2017,36(3):13-15,19.
[26]	Thurstone L L. The Vectors of Mind[M]. Chicago:Univ. Chicago Press, 1935.
[27]	张萍,张世军.新疆北部沙漠边缘植被恢复可能性初探[J]. 干旱环境监测, 2007,(2):97-101.Zhang P, Zhang S J. The research possibility of vegetation restoration at fringe of Gurbantonggut desaet[J]. Arid Environmental Monitoring, 2007,(2):97-101.
[28]	柴慧霞,周成虎,陈曦,等.基于地理格网的新疆地貌区划方法与实现[J]. 地理研究, 2008,(3):481-492,725-726.Chai H X, Zhou C H, Chen X, et al. The new methodology of geomorphologic zonalization in Xinjiang based on geographical grid[J]. Geographical Research, 2008,(3):481-492,725-726.
[29]	安成邦,张曼,王伟,等.新疆地理环境特征以及农牧格局的形成[J]. 中国科学:地球科学, 2020,50(2):295-304.An C B, Zhang M, Wang W, et al. The pattern of Xinjiang physical geography and its relationship with the temporal-spatial distribution of agriculture and husbandry[J]. Scientia Sinica (Terrae), 2020,50(2):95-304.
[30]	王科.新疆地形水循环生态特征与绿洲区划[J]. 才智, 2009, 20):256-257.Wang K. The ecological characteristics of topographic water cycle and oasis division in Xinjiang[J]. Ability and wisdom, 2009,(20):256-257.
[31]	何中声,刘金福,洪伟,等.泉州市鸟类多样性海拔梯度格局的研究[J]. 中南林业科技大学学报, 2012,32(6):188-191.He Z S, Liu J F, Hong W, et al. Study on altitudinal patterns of avian diversity in Quanzhou city[J]. Journal of Central South University of Forestry & Technology, 2012,32(6):188-191.
[32]	Cheviron Z A, Natarajan C, Projecto-Garcia J, et al. Integrating evolutionary and functional tests of adaptive hypotheses:A case study of altitudinal differentiation in hemoglobin function in an andean sparrow, zonotrichia capensis. Mol Biol Evol, 2014,31:2948-2962.
[33]	熊鹰,雷富民.鸟类对高海拔环境的适应性演化:从表型到基因组[J]. 中国科学:生命科学, 2019,49(4):361-370.Xiong Y, Lei F M. High-altitude adaptation in birds:From phenomics to genomics. Scientia Sinica (Vitae), 2019,49(4):361-370.
[34]	杜寅,周放,舒晓莲,等.全球气候变暖对中国鸟类区系的影响[J]. 动物分类学报, 2009,34(3):664-674.Du Y, Zhou F, Shu X L,et al. The impact of global warming on Chinese bird fauna[J]. Acta Zootaxonomica Sinica, 2009,34(3):64-674.