Applying BioMod for ModelEnsemble in Species Distributions: a Case Study for Tsuga chinensis in China

doi:10.7677/ynzwyj201312127

Abstract

Abstract:

The integration of new statistical techniques and increasing availability of multisources and multiscale data sets promote the development of species distribution modeling. Yet, choice of data sets, different model types and their underlying ecological theories and assumptions can cause uncertainty in model predictions. In order to decrease prediction uncertainty, studies using model ensemble are gaining in popularity. In this paper we apply the BioMod package developed under R environment to predict the spatial distribution of Tsuga chinensis using nine different models. Our aims were to evaluate model performance, select explanatory variables, and assemble the best predictive output. Random Forest, MARS and GAM performed the best amongst the nine models compared, while SRE was the worst. The ensemble models predicted that the areas of high probability for T.chinensis presence lie mainly in Southwest China and the periphery of the Sichuan basin, and are also distributed sporadically in South China and Taiwan. These predictions reflect the actual distribution pattern of T.chinensis, and show high agreement with other analyses. The application of BioMod for model ensemble lowers uncertainty and improves the prediction performance.

Key words: Species distribution model Tsuga chinensis, Model assembly, Biogeography, BioMod

摘要：

新型统计方法和多源、多尺度空间信息数据的产生促进了物种空间分布模型的快速发展。不同的物种空间分布模型在生态学理论的运用以及前提假设上存在差异。选用不同的模型方法和输入数据会带来预测结果的不确定性。对比并集成多个物种空间分布模型，同时利用多组输入数据可降低预测的不确定性，提高物种分布模拟的精度。本文以中国特有种铁杉（Tsuga chinensis）为例，运用基于R语言开发的BioMod软件包对比9个物种空间分布模型对铁杉的模拟效果。最后以曲线下面积（ROC）为权重集成9个模型的模拟结果，产生和筛选最佳的铁杉潜在空间分布图。研究发现随机森林模型（RF）的模拟效果最好，其次是多元适应回归样条函数模型（MARS）和广义相加模型（GAM），模拟效果最差的是表面分布区分室模型（SRE）。模型集成结果显示，最适宜铁杉分布的区域集中在中国的西南及四川盆地周围，其次零星分散于华南和台湾部分地区。这一结果与前人对铁杉自然分布的描述和研究结果较为吻合。研究进一步表明，通过模型的集成能有效地降低由于单个模型所带来的模拟结果不确定性，从而提高模拟的精度和效果。

关键词: 物种空间分布模型, 铁杉, 模型集成, 分布区, BioMod

CLC Number:

Q 948.2

BI Ying-Feng-, HU Jian-Chu-, LI Qiao-Hong-, Antoine Guisan, Wilfried Thuiller. Applying BioMod for ModelEnsemble in Species Distributions: a Case Study for Tsuga chinensis in China[J]. Plant Diversity, 2013, 35(5): 647-655.

毕迎凤1、2, 许建初3, 李巧宏1, Antoine Guisan4, Wilfried Thuiller5. 应用BioMod集成多种模型研究物种的空间分布——以铁杉在中国的潜在分布为例[J]. Plant Diversity, 2013, 35(5): 647-655.

References

郑万钧, 傅立国, 1978. 中国植物志 (第7卷) ［M］. 北京: 科学出版社
Allouche O, Tsoar A, Kadmon R, 2006. Assessing the accuracy of species distribution models: prevalence, kappa and the true skill statistic (TSS) ［J］. Journal of Applied Ecology, 43 (6): 1223—1232
Araújo MB, New M, 2007. Ensemble forecasting of species distributions［J］. Trends in Ecology and Evolution, 22 (1): 42—47
Austin M, 2007. Species distribution models and ecological theory: a critical assessment and some possible new approaches［J］. Ecological Modelling, 200 (1-2): 1—19
Austin MP, 2002. Spatial prediction of species distribution: an interface between ecological theory and statistical modeling［J］. Ecological Modelling, 157(2-3): 101—118
Austin MP, Van Niel KP, 2011. Improving species distribution models for climate change studies: variable selection and scale［J］. Journal of Biogeography, 38 (1): 1—8
Bannister P, Neuner G, Bigras F et al., 2001. Frost Resistance and the Distribution of Conifers, Conifer Cold Hardiness［M］. Spuiboulevard: Kluwer Academic Publishers, 3—21
BarbetMassin M, Jiguet F, Albert CH et al., 2012. Selecting pseudoabsences for species distribution models: how, where and how many? ［J］. Methods in Ecology and Evolution, 3 (2): 327—338
Barry S, Elith J, 2006. Error and uncertainty in habitat models［J］. Journal of Applied Ecology, 43 (3): 413—423
Bellard C, Bertelsmeier C, Leadley P et al., 2012. Impacts of climate change on the future of biodiversity［J］. Ecology Letters, 15 (4): 365—377
Breiman L, 2001. Random forests［J］. Machine Learning, 45 (1): 5—32
Breiman L, Friedman J, Olshen R et al., 1999. Classification and Regression Trees［M］. New York: CRC Press
Brotons L, Thuiller W, Araújo MB et al., 2004. Presenceabsence versus presenceonly modelling methods for predicting bird habitat suitability［J］. Ecography, 27 (4): 437—448
Buisson L, Thuiller W, Casajus N et al., 2010. Uncertainty in ensemble forecasting of species distribution［J］. Global Change Biology, 16 (4): 1145—1157
Busby JR, 1991. BIOCLIMa bioclimate analysis and prediction system［J］. Plant Protection Quarterly, 6 (1): 8—9
Canhos VP, Souza Sd, Giovanni RD et al., 2004. Global Biodiversity Informatics: setting the scene for a “new world” of ecological forecasting［J］. Biodiversity Informatics, 1: 1—13
Del Tredici P, Kitajima A, 2004. Introduction and cultivation of Chinese hemlock (Tsuga chinensis) and its resistance to hemlock woolly adelgid (Adelges tsugae) ［J］. Journal of Arboriculture, 30 (5): 282—287
Elith J, Graham HC, Anderson PR et al., 2006. Novel methods improve prediction of species’ distributions from occurrence data［J］. Ecography, 29 (2): 129—151
Fielding AH, Bell JF, 1997. A review of methods for the assessment of prediction errors in conservation presence/absence models［J］. Environmental Conservation, 24 (1): 38—49
Franklin J, 1998. Predicting the distribution of shrub species in southern California from climate and terrainderived variables (abstract GEOBASE) ［J］. Journal of Vegetation Science, 9 (5): 733—748
Friedman JH, 1991. Multivariate adaptive regression splines［J］. The Annals of Statistics, 19 (1): 1—67
Gallien L, Münkemüller T, Albert CH et al., 2010. Predicting potential distributions of invasive species: where to go from here? ［J］. Diversity and Distributions, 16 (3): 331—342
Guisan A, Thuiller W, 2005. Predicting species distribution: offering more than simple habitat models［J］. Ecology Letters, 8 (9): 993—1009
Guisan A, Zimmermann NE, 2000. Predictive habitat distribution models in ecology［J］. Ecological Modelling, 135 (2-3): 147—186
Hastie T, Tibshirani R, Buja A, 1994. Flexible discriminant analysis by optimal scoring［J］. Journal of the American Statistical Association, 89 (428): 1255—1270
Hastie TJ, Tibshirani R, 1990. Generalized Additive Models［M］. London: Chapman & Hall/CRC
Heibl C, Renner SS, 2012. Distribution models and a dated phylogeny for Chilean Oxalis species reveal occupation of new habitats by different lineages, not rapid adaptive radiation［J］. Systematic Biology, 61 (5): 823—834
Leathwick JR, Elith J, Hastie T, 2006. Comparative performance of generalized additive models and multivariate adaptive regression splines for statistical modelling of species distributions［J］. Ecological Modelling, 199 (2): 188—196
Loiselle BA, Jrgensen PM, Consiglio T et al., 2008. Predicting species distributions from herbarium collections: does climate bias in collection sampling influence model outcomes? ［J］. Journal of Biogeography, 35 (1): 105—116
Maiorano L, Cheddadi R, Zimmermann NE et al., 2012. Building the niche through time: using 13000 years of data to predict the effects of climate change on three tree species in Europe［J］. Global Ecology and Biogeography: http://wileyonlinelibrary.com/journal/geb
Marmion M, Luoto M, Heikkinen RK, 2009. The performance of stateoftheart modelling techniques depends on geographical distribution of species［J］. Ecological Modelling, 220 (24): 3512—3520
McCullagh P, Nelder JA, 1989. Generalized Linear Models［M］. London: Chapman & Hall/CRC, 35
McPherson JM, Jetz W, 2007. Effects of species’ ecology on the accuracy of distribution models［J］. Ecography, 30 (1): 135—151
Naimi B, Skidmore AK, Groen TA et al., 2011. Spatial autocorrelation in predictors reduces the impact of positional uncertainty in occurrence data on species distribution modeling［J］. Journal of Biogeography, 38 (8): 1497—1509
Petitpierre B, Kueffer C, Broennimann O et al., 2012. Climatic niche shifts are rare among terrestrial plant invaders［J］. Science, 335 (6074): 1344—1348
Phillips SJ, Anderson RP, Schapire RE, 2006. Maximum entropy modeling of species geographic distributions［J］. Ecological Modelling, 190 (3-4): 231—259
Phillips SJ, Miroslav D, Jane E et al., 2009. Sample selection bias and presenceonly distribution models: implications for background and pseudoabsence data［J］. Ecological Applications, 19 (1): 181—197
Prasad A, Iverson L, Liaw A, 2006. Newer classification and regression tree techniques: bagging and random forests for ecological prediction［J］. Ecosystems, 9 (2): 181—199
Pulliam HR, 2000. On the relationship between niche and distribution［J］. Ecology Letters, 3 (4): 349—361
Ridgeway G, 1999. The state of boosting［J］. Computing Science and Statistics, 31: 172—181
Ripley BD, 1996. Pattern Recognition and Neural Networkds［M］. London: Cambridge University Press
Schmidt M, Kreft H, Thiombiano A et al., 2005. Herbarium collections and field databased plant diversity maps for Burkina Faso［J］. Diversity and Distributions, 11 (6): 509—516
Smith SA, Donoghue MJ, 2010. Combining historical biogeography with niche modeling in the Caprifolium clade of Lonicera (Caprifoliaceae, Dipsacales) ［J］. Systematic Biology, 59 (3): 322—341
Thuiller W, 2004. Patterns and uncertainties of species’ range shifts under climate change［J］. Global Change Biology, 10 (12): 2020—2027
Thuiller W, Lafourcade B, Engler R et al., 2009. BIOMOD-a platform for ensemble forecasting of species distributions［J］. Ecography, 32 (3): 369—373
Václavík T, Meentemeyer RK, 2012. Equilibrium or not? Modelling potential distribution of invasive species in different stages of invasion［J］. Diversity and Distributions, 18 (1): 73—83
Van Horssen PW, Pebesma EJ, Schot PP, 2002. Uncertainties in spatially aggregated predictions from a logistic regression model［J］. Ecological Modelling, 154 (1-2): 93—101
Wiens JA, Stralberg D, Jongsomjit D et al., 2009. Niches, models, and climate change: Assessing the assumptions and uncertainties［J］. Proceedings of the National Academy of Sciences of the United States of America, 106 (2): 19729—19736
Williams KJ, Belbin L, Austin MP et al., 2012. Which environmental variables should I use in my biodiversity model? ［J］. International Journal of Geographical Information Science, 26 (11): 2009—2047
Ying JS (应俊生), 1989. Areography of the gymnosperms of China (1)-distribution of the Pinaceae of China［J］. Acta Phytotaxonomic Sinica (植物分类学报), 27 (1): 27—38

[1]	Ibrokhimjon Ergashov, Ziyoviddin Yusupov, Alireza Dolatyari, Mina Khorasani, İsmail Eker, Nazgul Turdumatova, Georgy Lazkov, Farruhbek Rasulov, Hang Sun, Tao Deng, Komiljon Tojibaev. New insights into the molecular phylogeny and biogeographical history of Allium subgenus Melanocrommyum (Amaryllidaceae) based on plastome and nuclear sequences [J]. Plant Diversity, 2025, 47(04): 561-575.
[2]	Lang Li (李朗), Bing Liu (刘冰), Yu Song (宋钰), Hong-Hu Meng (孟宏虎), Xiu-Qin Ci (慈秀芹), John G. Conran, Rogier P.J. de Kok, Pedro Luís Rodrigues de Moraes, Jun-Wei Ye (叶俊伟), Yun-Hong Tan (谭运洪), Zhi-Fang Liu (刘志芳), Marlien van der Merwe, Henk van der Werff, Yong Yang (杨永), Jens G. Rohwer, Jie Li (李捷). Global advances in phylogeny, taxonomy and biogeography of Lauraceae [J]. Plant Diversity, 2025, 47(03): 341-364.
[3]	Kai Chen, Yan-Chun Liu, Yue Huang, Xu-Kun Wu, Hai-Ying Ma, Hua Peng, De-Zhu Li, Peng-Fei Ma. Reassessing the phylogenetic relationships of Pseudosorghum and Saccharinae (Poaceae) using plastome and nuclear ribosomal sequences [J]. Plant Diversity, 2025, 47(03): 382-393.
[4]	Zengke Zhang, Wensheng Chen, Zengyan Li, Wentao Ren, Ling Mou, Junyong Zheng, Tian Zhang, Hantang Qin, Liyi Zhou, Bile Sai, Hang Ci, Yongchuan Yang, Shekhar R. Biswas, Enrong Yan. The island rule-like patterns of plant size variation in a young land-bridge archipelago: Roles of environmental circumstance and biotic competition [J]. Plant Diversity, 2025, 47(02): 300-310.
[5]	Wei Gu, Ting Zhang, Shui-Yin Liu, Qin Tian, Chen-Xuan Yang, Qing Lu, Xiao-Gang Fu, Heather R. Kates, Gregory W. Stull, Pamela S. Soltis, Douglas E. Soltis, Ryan A. Folk, Robert P. Guralnick, De-Zhu Li, Ting-Shuang Yi. Phylogenomics, reticulation, and biogeographical history of Elaeagnaceae [J]. Plant Diversity, 2024, 46(06): 683-697.
[6]	Yanwei Guan, Yongru Wu, Zheng Cao, Zhifeng Wu, Fangyuan Yu, Haibin Yu, Tiejun Wang. Island biogeography theory and the habitat heterogeneity jointly explain global patterns of Rhododendron diversity [J]. Plant Diversity, 2024, 46(05): 565-574.
[7]	Yajun Wang, Hanchen Wang, Chao Ye, Zhiping Wang, Chongbo Ma, Dongliang Lin, Xiaohua Jin. Progress in systematics and biogeography of Orchidaceae [J]. Plant Diversity, 2024, 46(04): 425-434.
[8]	Hui Feng, Achyut Kumar Banerjee, Wuxia Guo, Yang Yuan, Fuyuan Duan, Wei Lun Ng, Xuming Zhao, Yuting Liu, Chunmei Li, Ying Liu, Linfeng Li, Yelin Huang. Origin and evolution of a new tetraploid mangrove species in an intertidal zone [J]. Plant Diversity, 2024, 46(04): 476-490.
[9]	Yanjun Du, Rongchen Zhang, Xinran Tang, Xinyang Wang, Lingfeng Mao, Guoke Chen, Jiangshan Lai, Keping Ma. The mid-domain effect in flowering phenology [J]. Plant Diversity, 2024, 46(04): 502-509.
[10]	Tao Yang, Jia-Hao Cai, Yan-Zhi Dai, Hong-Yu Chen, Lei Han, Li Zhang, Wei-Yu Liang, Xu-Jun Li, Wen-Jia Li, Jing-Yu Wu, San-Ping Xie, De-Fei Yan. Megafossils of Betulaceae from the Oligocene of Qaidam Basin and their paleoenvironmental and phytogeographic implications [J]. Plant Diversity, 2024, 46(01): 101-115.
[11]	Zhe Chen, Zhuo Zhou, Ze-Min Guo, Truong Van Do, Hang Sun, Yang Niu. Historical development of karst evergreen broadleaved forests in East Asia has shaped the evolution of a hemiparasitic genus Brandisia (Orobanchaceae) [J]. Plant Diversity, 2023, 45(05): 501-512.
[12]	Xing Liu, Hui-Min Cai, Wen-Qiao Wang, Wei Lin, Zhi-Wei Su, Zhong-Hui Ma. Why is the beautyberry so colourful? Evolution, biogeography, and diversification of fruit colours in Callicarpa (Lamiaceae) [J]. Plant Diversity, 2023, 45(01): 6-19.
[13]	Li-Guo Zhang, Xiao-Qian Li, Wei-Tao Jin, Yu-Juan Liu, Yao Zhao, Jun Rong, Xiao-Guo Xiang. Asymmetric migration dynamics of the tropical Asian and Australasian floras [J]. Plant Diversity, 2023, 45(01): 20-26.
[14]	Sanchita Kumar, Taposhi Hazra, Robert A. Spicer, Manoshi Hazra, Teresa E. V. Spicer, Subir Bera, Mahasin Ali Khan. Coryphoid palms from the K-Pg boundary of central India and their biogeographical implications: Evidence from megafossil remains [J]. Plant Diversity, 2023, 45(01): 80-97.
[15]	Changkyun Kim, Dong-Kap Kim, Hang Sun, Joo-Hwan Kim. Phylogenetic relationship, biogeography, and conservation genetics of endangered Fraxinus chiisanensis (Oleaceae), endemic to South Korea [J]. Plant Diversity, 2022, 44(02): 170-180.