Predicting the potential distribution of bamboo with species distribution models

Using history climate data and two representative climate change scenarios, we predicted the potential distribution of bamboo in China from 1961 to 2099 based on specie distribution models. Through evaluating the impact of presence-only, true-absence and pseudo-absence data on SVM models accuracy on the potential distribution of bamboo during 1981-2000, we found that the two-class SVM using presence and pseudo-absence data showed the finest performance in forecasting potential distribution of bamboo. The prediction results of spatial pattern and inter-annual variation of potential distribution of bamboo under history and future climate showed that, the potential distribution of bamboo increased by 91500 km2 from 1961 to 2000. In climate change scenario B1, the potential distribution area increased 2433 km2 per year. In A2 scenario, the annual increment of potential distribution area was 13825 km2. Furthermore, the potential distribution of bamboo showed a northward migration obviously in both history climate and future scenarios.

[1]  Guomo Zhou,et al.  Carbon sequestration by Chinese bamboo forests and their ecological benefits: assessment of potential, problems, and future challenges , 2011 .

[2]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[3]  T. Dawson,et al.  Modelling species distributions in Britain: a hierarchical integration of climate and land-cover data , 2004 .

[4]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[5]  M. Edwards,et al.  Impact of climate change on marine pelagic phenology and trophic mismatch , 2004, Nature.

[6]  Nello Cristianini,et al.  Support Vector Machines and Kernel Methods: The New Generation of Learning Machines , 2002, AI Mag..

[7]  M. Hutchinson,et al.  Splines — more than just a smooth interpolator , 1994 .

[8]  A. Peterson,et al.  Ecological niches as stable distributional constraints on mammal species, with implications for Pleistocene extinctions and climate change projections for biodiversity , 2004 .

[9]  A. Townsend Peterson,et al.  Novel methods improve prediction of species' distributions from occurrence data , 2006 .

[10]  David R. B. Stockwell,et al.  Future projections for Mexican faunas under global climate change scenarios , 2002, Nature.

[11]  J. Elith,et al.  Predictions and their validation: Rare plants in the Central Highlands, Victoria, Australia , 2002 .

[12]  J. Palutikof,et al.  Climate change 2007 : impacts, adaptation and vulnerability , 2001 .

[13]  C. Graham,et al.  Habitat history improves prediction of biodiversity in rainforest fauna. , 2006, Proceedings of the National Academy of Sciences of the United States of America.