View More View Less
  • 1 Sapienza University of Rome Department of Plant Biology P.le A. Moro, 5 00185 Rome Italy
  • 2 Sapienza University of Rome Department of Experimental Medicine — Statistics Unit P.le A. Moro, 5 00185 Rome Italy
Restricted access

Spatial distribution modelling can be a useful tool for elaborating conservation strategies for tree species characterized by fragmented and sparse populations. We tested five statistical models—Support Vector Regression (SVR), Multivariate Adaptive Regression Splines (MARS), Gaussian processes with radial basis kernel functions (GP), Regression Tree Analysis (RTA) and Random Forests (RF)—for their predictive performances. To perform the evaluation, we applied these techniques to three tree species for which conservation measures should be elaborated and implemented: one Mediterranean species ( Quercus suber ) and two temperate species ( Ilex aquifolium and Taxus baccata ). Model evaluation was measured by MSE, Goodman-Kruskal and sensitivity statistics and map outputs based on the minimal predicted area criterion. All the models performed well, confirming the validity of this approach when dealing with species characterized by narrow and specialized niches and when adequate data (more than 40–50 samples) and environmental and climatic variables, recognized as important determinants of plant distribution patterns, are available. Based on the evaluation processes, RF resulted the most accurate algorithm thanks to bootstrap-resampling, trees averaging, randomization of predictors and smoother response surface.

  • Araújo, M. B. and A. Guisan. 2006. Five (or so) challenges for species distribution modeling. J. Biogeogr. 33: 1677–1688.

    Guisan A. , 'Five (or so) challenges for species distribution modeling ' (2006 ) 33 J. Biogeogr. : 1677 -1688.

    • Search Google Scholar
  • Araújo, M. B. and M. New. 2007. Ensemble forecasting of species distributions. Trends Ecol. Evol. 22(1): 42–47.

    New M. , 'Ensemble forecasting of species distributions ' (2007 ) 22 Trends Ecol. Evol. : 42 -47.

    • Search Google Scholar
  • Attorre, F., M. Alfò, M. De Sanctis, F. Francesconi and F. Bruno. 2007a. Comparison of interpolation methods for mapping climatic and bioclimatic variables at regional scale. International J. Climatol. 27: 1825–1843.

    Bruno F. , 'Comparison of interpolation methods for mapping climatic and bioclimatic variables at regional scale ' (2007 ) 27 International J. Climatol. : 1825 -1843.

    • Search Google Scholar
  • Attorre, F., F. Francesconi, N. Taleb, P. Scholte, A. Saed, M. Alfo and F. Bruno. 2007b. Will dragonblood survive the next period of climate change? Current and future potential distribution of Dracaena cinnabari (Socotra, Yemen). Biol. Conserv. 138: 430–439.

    Bruno F. , 'Will dragonblood survive the next period of climate change? Current and future potential distribution of Dracaena cinnabari (Socotra, Yemen) ' (2007 ) 138 Biol. Conserv. : 430 -439.

    • Search Google Scholar
  • Beaumont, L.J., L. Hughes, and M. Poulsen. 2005. Predicting species distributions: use of climatic parameters in BIOCLIM and its impact on predictions of species’ current and future distributions. Ecol. Model. 186: 250–269.

    Poulsen M. , 'Predicting species distributions: use of climatic parameters in BIOCLIM and its impact on predictions of species’ current and future distributions ' (2005 ) 186 Ecol. Model. : 250 -269.

    • Search Google Scholar
  • Benito Garzòn, M., R. Blazek, M. Neteler, R. Sánchez de Dios, H. Sainz Ollero and C. Furlanello. 2006. Machine learning models for predicting species habitat distribution suitability: An example with Pinus sylvestris L. for the Iberian Peninsula. Ecol. Model. 197: 383–393.

    Furlanello C. , 'Machine learning models for predicting species habitat distribution suitability: An example with Pinus sylvestris L. for the Iberian Peninsula ' (2006 ) 197 Ecol. Model. : 383 -393.

    • Search Google Scholar
  • Benito Garzòn, M., R. Sánchez de Dios and H. Sainz Ollero. 2008. Effects of climate change on the distribution of Iberian tree species. Appl. Veg. Sci. 11: 169–178.

    Sainz Ollero H. , 'Effects of climate change on the distribution of Iberian tree species ' (2008 ) 11 Appl. Veg. Sci. : 169 -178.

    • Search Google Scholar
  • Breiman, L. 2001. Random forests. Machine Learning 45: 5–32.

    Breiman L. , 'Random forests ' (2001 ) 45 Machine Learning : 5 -32.

  • Breiman, L., J. H. Friedman, R. A. Olshen and C. J. Stone. 1984. Classification and Regression Trees . Wadsworth, Belmont, CA.

    Stone C. J. , '', in Classification and Regression Trees , (1984 ) -.

  • Chefaoui, R.M. and J.M. Lobo. 2008. Assessing the effects of pseudo-absences on predictive distribution model performance. Ecol. Model . 210: 478–486.

    Lobo J.M. , 'Assessing the effects of pseudo-absences on predictive distribution model performance ' (2008 ) 210 Ecol. Model : 478 -486.

    • Search Google Scholar
  • Drake, J.M., C. Randin and A. Guisan. 2006. Modelling ecological niches with support vector machines. J. Appl. Ecol. 43: 424–432.

    Guisan A. , 'Modelling ecological niches with support vector machines ' (2006 ) 43 J. Appl. Ecol. : 424 -432.

    • Search Google Scholar
  • Drucker, H., C.J.C. Burges, L. Kaufman, A. Smola and V. Vapnik. 1997. Support Vector Regression Machines . Advances in Neural Information Processing Systems 9, NIPS 1996, pp. 155–161.

  • Elith, J., M.A. Burgman and H.M. Regan. 2002. Mapping epistemic uncertainties and vague concepts in predictions of species distribution. Ecol. Model. 157: 313–330.

    Regan H.M. , 'Mapping epistemic uncertainties and vague concepts in predictions of species distribution ' (2002 ) 157 Ecol. Model. : 313 -330.

    • Search Google Scholar
  • Elith, J., C. H. Graham, R. P. Anderson, M. Dudýk, S. Ferrier, A. Guisan, R. J. Hijmans, F. Huettmann, J.R. Leathwick, A. Lehmann, J. Li, L. G. Lohmann, B. A. Loiselle, G. Manion, C. Moritz, M. Nakamura, Y. Nakazawa, J. McC. Overton, A. Townsend Peterson, S. J. Phillips, K. Richardson, R. Scachetti-Pereira, R. E. Schapire, J. Soberòn, S. Williams, M. S. Wisz and N.E. Zimmermann. 2006. Novel methods improve prediction of species’ distributions from occurrence data. Ecography 29: 129–151.

    Zimmermann N.E. , 'Novel methods improve prediction of species’ distributions from occurrence data ' (2006 ) 29 Ecography : 129 -151.

    • Search Google Scholar
  • Elith, J. and J. Leathwick. 2007. Predicting species distributions from museum and herbarium records using multiresponse models fitted with multivariate adaptive regression splines. Divers. Distrib. 13: 265–275.

    Leathwick J. , 'Predicting species distributions from museum and herbarium records using multiresponse models fitted with multivariate adaptive regression splines ' (2007 ) 13 Divers. Distrib. : 265 -275.

    • Search Google Scholar
  • Engler, R., A. Guisan and L. Rechsteiner. 2004. An improved approach for predicting the distribution of rare and endangered species from occurrence and pseudo-absence data. J. Appl. Ecol. 41: 263–274.

    Rechsteiner L. , 'An improved approach for predicting the distribution of rare and endangered species from occurrence and pseudo-absence data ' (2004 ) 41 J. Appl. Ecol. : 263 -274.

    • Search Google Scholar
  • Farber, O. and R. Kadmon. 2003. Assessment of alternative approaches for bioclimatic modelling with special emphasis on the Mahalanobis distance. Ecol. Model. 160: 115–130.

    Kadmon R. , 'Assessment of alternative approaches for bioclimatic modelling with special emphasis on the Mahalanobis distance ' (2003 ) 160 Ecol. Model. : 115 -130.

    • Search Google Scholar
  • Friedman, J. 1991. Multivariate adaptive regression splines. Ann. Stat. 19: 1–141

    Friedman J. , 'Multivariate adaptive regression splines ' (1991 ) 19 Ann. Stat. : 1 -141.

  • Guisan, A. and N. E. Zimmerman. 2000. Predictive habitat distribution models in ecology. Ecol. Model. 135: 147–186.

    Zimmerman N. E. , 'Predictive habitat distribution models in ecology ' (2000 ) 135 Ecol. Model. : 147 -186.

    • Search Google Scholar
  • Guisan A., T.C. Edwards and T. Hastie. 2002. Generalized linear and generalized additive models in studies of species distribution: setting the scene. Ecol. Model. 157: 89–100.

    Hastie T. , 'Generalized linear and generalized additive models in studies of species distribution: setting the scene ' (2002 ) 157 Ecol. Model. : 89 -100.

    • Search Google Scholar
  • Guisan, A. and W. Thuiller. 2005. Predicting species distribution: offering more than simple habitat models. Ecol. Lett. 8: 993–1009.

    Thuiller W. , 'Predicting species distribution: offering more than simple habitat models ' (2005 ) 8 Ecol. Lett. : 993 -1009.

    • Search Google Scholar
  • Guisan, A., O. Broennimann, R. Engler, M. Vust, N.G. Yoccoz, A. Lehmann and N.E. Zimmermann. 2006. Using niche-based models to improve the sampling of rare species. Conserv. Biol. 20: 501–511.

    Zimmermann N.E. , 'Using niche-based models to improve the sampling of rare species ' (2006 ) 20 Conserv. Biol. : 501 -511.

    • Search Google Scholar
  • Guisan, A., N. E. Zimmermann, J. Elith, C. H. Graham, S. Phillips and A. T. Peterson. 2007. What matters for predicting the occurrences of trees: techniques, data or species characteristics? Ecol. Monogr. 77: 615–630.

    Peterson A. T. , 'What matters for predicting the occurrences of trees: techniques, data or species characteristics? ' (2007 ) 77 Ecol. Monogr. : 615 -630.

    • Search Google Scholar
  • Guo, Q., M. Kelly and C. H. Graham. 2005. Support vector machines for predicting distribution of Sudden Oak Death in California. Ecol. Model. 182: 75–90.

    Graham C. H. , 'Support vector machines for predicting distribution of Sudden Oak Death in California ' (2005 ) 182 Ecol. Model. : 75 -90.

    • Search Google Scholar
  • Hastie, T., R. Tibshirani, and J. Friedman. 2001. The Elements of Statistical Learning . Springer, New York.

    Friedman J. , '', in The Elements of Statistical Learning , (2001 ) -.

  • Hernandez, P. A., C. H. Graham, L. L. Master and D. L. Albert. 2006. The effect of sample size and species characteristics on performance of different species distribution modelling methods. Ecography 29: 773–785.

    Albert D. L. , 'The effect of sample size and species characteristics on performance of different species distribution modelling methods ' (2006 ) 29 Ecography : 773 -785.

    • Search Google Scholar
  • Hidalgo, P.J., M.J. Marìn, J. Quiijada and J.M. Moreira. 2008. A spatial distribution model of cork oak ( Quercus suber ) in southwestern Spain: a suitable tool for reforestation. Forest Ecol. Manage. 255: 25–34.

    Moreira J.M. , 'A spatial distribution model of cork oak (Quercus suber) in southwestern Spain: a suitable tool for reforestation ' (2008 ) 255 Forest Ecol. Manage. : 25 -34.

    • Search Google Scholar
  • Hirzel, A. H., J. Hausser, D. Chessel and N. Perrin. 2002. Ecological-niche factor analysis: how to compute habitat-suitability maps without absence data? Ecology 83: 2027–2036.

    Perrin N. , 'Ecological-niche factor analysis: how to compute habitat-suitability maps without absence data? ' (2002 ) 83 Ecology : 2027 -2036.

    • Search Google Scholar
  • Iverson, L.R. and A.M. Prasad. 1998. Predicting abundance of 80 tree species following climate change in the Eastern United States. Ecol. Monogr. 68: 465–485.

    Prasad A.M. , 'Predicting abundance of 80 tree species following climate change in the Eastern United States ' (1998 ) 68 Ecol. Monogr. : 465 -485.

    • Search Google Scholar
  • Iverson, L.R. and A.M. Prasad. 2002. Potential redistribution of tree species habitat under five climate change scenarios in the Eastern United States. Forest Ecol. Manage. 155: 205–222.

    Prasad A.M. , 'Potential redistribution of tree species habitat under five climate change scenarios in the Eastern United States ' (2002 ) 155 Forest Ecol. Manage. : 205 -222.

    • Search Google Scholar
  • Iverson, L.R., A.M. Prasad and M.K. Schwartz. 1999. Modelling potential future individual tree species distributions in the Eastern United States under a climate change scenario: a case study with Pinus virginiana . Ecol. Model. 115: 77–93.

    Schwartz M.K. , 'Modelling potential future individual tree species distributions in the Eastern United States under a climate change scenario: a case study with Pinus virginiana ' (1999 ) 115 Ecol. Model. : 77 -93.

    • Search Google Scholar
  • Leathwick, J. R., D. Rowe, J. Richardson, J. Elith and T. Hastie. 2005. Using multivariate adaptive regression splines to predict the distributions of New Zealand’s freshwater diadromous fish. Freshwater Biol. 50: 2034–2052.

    Hastie T. , 'Using multivariate adaptive regression splines to predict the distributions of New Zealand’s freshwater diadromous fish ' (2005 ) 50 Freshwater Biol. : 2034 -2052.

    • Search Google Scholar
  • Lehmann, A., J. M. Overton and M. P. Austin. 2002. Regression models for spatial prediction: their role for biodiversity and conservation. Biodivers. Conserv. 11: 2085–2092.

    Austin M. P. , 'Regression models for spatial prediction: their role for biodiversity and conservation ' (2002 ) 11 Biodivers. Conserv. : 2085 -2092.

    • Search Google Scholar
  • Luoto, M., J. Pöyry, R. K. Heikkinen and K. Saarinen. 2005. Uncertainty of bioclimate envelope models based on the geographical distribution of species. Global Ecol. Biogeogr. 14: 575–584.

    Saarinen K. , 'Uncertainty of bioclimate envelope models based on the geographical distribution of species ' (2005 ) 14 Global Ecol. Biogeogr. : 575 -584.

    • Search Google Scholar
  • Magri, D., G. G. Vendramin, B. Comps, I. Dupanloup, T. Geburek, D. Gomory, M. Latalowa, T. Litt, L. Paule, J. M. Roure, I. Tantau, W. O. Van der Knaap, R. J. Petit and J. L. De Beaulieu. 2006. A new scenario for the Quaternary history of European beech populations: palaeobotanical evidence and genetic consequences. New Phytol. 171: 199–221.

    Beaulieu J. L. , 'A new scenario for the Quaternary history of European beech populations: palaeobotanical evidence and genetic consequences ' (2006 ) 171 New Phytol. : 199 -221.

    • Search Google Scholar
  • Müller, K. R., S. Mika, G. Rätsch, K. Tsuda. and B. Schölkopf. 2001. An introduction to kernel-based learning algorithms. IEEE Transactions on Neural Networks 12: 181–202.

    Schölkopf B. , 'An introduction to kernel-based learning algorithms ' (2001 ) 12 IEEE Transactions on Neural Networks : 181 -202.

    • Search Google Scholar
  • Pearce, J. and M. Boyce. 2006. Modelling distribution and abundance with presence-only data. J. Appl. Ecol. 43: 405–412.

    Boyce M. , 'Modelling distribution and abundance with presence-only data ' (2006 ) 43 J. Appl. Ecol. : 405 -412.

    • Search Google Scholar
  • Pearson, R.G., T.P. Dawson, P.M. Berry and P.A. Harrison. 2002. SPECIES: a spatial evaluation of climate impact on the envelope of species. Ecol. Model. 154: 289–300.

    Harrison P.A. , 'SPECIES: a spatial evaluation of climate impact on the envelope of species ' (2002 ) 154 Ecol. Model. : 289 -300.

    • Search Google Scholar
  • Peterson, A.T., V. Sanchez-Cordero, J. Soberòn, J. Bartley, R. W. Buddemeier and A. G. Navarro-Sigüenza. 2001. Effects of global climate change on geographic distributions of Mexican Cracidae. Ecol. Model. 144: 21–30.

    Navarro-Sigüenza A. G. , 'Effects of global climate change on geographic distributions of Mexican Cracidae ' (2001 ) 144 Ecol. Model. : 21 -30.

    • Search Google Scholar
  • Peterson, A.T., M.A. Ortega-Huerta, Bartley J. V. Sánchez-Cordero, J. Soberón, R. H. Buddemeier and D. R. B. Stockwell. 2002. Future projections for Mexican faunas under global climate change scenarios. Nature 416: 626–629.

    Stockwell D. R. B. , 'Future projections for Mexican faunas under global climate change scenarios ' (2002 ) 416 Nature : 626 -629.

    • Search Google Scholar
  • Prasad, A. M., L. R. Iverson and A. Liaw. 2006. Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9: 181–199.

    Liaw A. , 'Newer classification and regression tree techniques: bagging and random forests for ecological prediction ' (2006 ) 9 Ecosystems : 181 -199.

    • Search Google Scholar
  • Recknagel, F. 2001. Applications of machine learning to ecological modelling. Ecol. Model. 146: 303–310.

    Recknagel F. , 'Applications of machine learning to ecological modelling ' (2001 ) 146 Ecol. Model. : 303 -310.

    • Search Google Scholar
  • Rouget, M., D. M. Richardson, J. L. Nel, D. C. Le Maitre, B. Egoh and T. Mgidi. 2004. Mapping the potential ranges of major plant invaders in South Africa, Lesotho and Swaziland using climatic suitability. Divers. Distrib. 10: 475–484.

    Mgidi T. , 'Mapping the potential ranges of major plant invaders in South Africa, Lesotho and Swaziland using climatic suitability ' (2004 ) 10 Divers. Distrib. : 475 -484.

    • Search Google Scholar
  • Scarnati, L., F. Attorre, M. De Sanctis, A. Farcomeni, F. Francesconi, M. Mancini and F. Bruno. 2009. A multiple approach for the evaluation of the spatial distribution and dynamics of a forest habitat: the case of Apennine beech forests with Taxus baccata and Ilex aquifolium . Biodivers. Conserv . Doi: 10.1007/s10531-009-9629-z

  • Segurado, P. and M. B. Araujo. 2004. An evaluation of methods for modelling species distributions. J. Biogeogr. 31: 1555–1568.

    Araujo M. B. , 'An evaluation of methods for modelling species distributions ' (2004 ) 31 J. Biogeogr. : 1555 -1568.

    • Search Google Scholar
  • Thuiller, W. 2003. BIOMOD — Optimizing predictions of species distributions and projecting potential future shifts under global change. Global Change Biol. 9: 1353–1362.

    Thuiller W. , 'BIOMOD — Optimizing predictions of species distributions and projecting potential future shifts under global change ' (2003 ) 9 Global Change Biol. : 1353 -1362.

    • Search Google Scholar
  • Thuiller, W., J. Vayreda, J. Pino, S. Sabate, S. Lavorel and C. Gracia. 2003. Large-scale environmental correlates of forest tree distributions in Catalonia (NE Spain). Global Ecol. Biogeogr. 12: 313–325.

    Gracia C. , 'Large-scale environmental correlates of forest tree distributions in Catalonia (NE Spain) ' (2003 ) 12 Global Ecol. Biogeogr. : 313 -325.

    • Search Google Scholar
  • Thuiller, W., S. Lavorel, G.F. Midgley, S. Lavergne and A.G. Rebelo. 2004. Relating plant traits and species distributions along bioclimatic gradients for 88 Leucadendron species in the Cape Floristic Region. Ecology 85: 1688–1699.

    Rebelo A.G. , 'Relating plant traits and species distributions along bioclimatic gradients for 88 Leucadendron species in the Cape Floristic Region ' (2004 ) 85 Ecology : 1688 -1699.

    • Search Google Scholar
  • Tsoar, A., O. Allouche, O. Steinitz, D. Rotem and R. Kadmon. 2007. A comparative evaluation of presence only methods for modelling species distribution. Divers. Distrib. 13: 397–405.

    Kadmon R. , 'A comparative evaluation of presence only methods for modelling species distribution ' (2007 ) 13 Divers. Distrib. : 397 -405.

    • Search Google Scholar
  • Vayssieres, M.P., R.E. Richard and B.H. Allen-Diaz. 2000. Classification trees: an alternative non-parametric approach for predicting species distribution. J. Veg. Sci. 11: 679–694.

    Allen-Diaz B.H. , 'Classification trees: an alternative non-parametric approach for predicting species distribution ' (2000 ) 11 J. Veg. Sci. : 679 -694.

    • Search Google Scholar
  • Ward, G., T. Hastie, S. Barry, J. Elith, and J. Leathwick. 2009. Presence-only data and the EM algorithm. Biometrics 65: 554–563.

    Leathwick J. , 'Presence-only data and the EM algorithm ' (2009 ) 65 Biometrics : 554 -563.

  • Williams, C. K. I. and D. Barber. 1998: Bayesian classification with Gaussian processes. IEEE Transactions on Pattern Analysis and Machine Intelligence 20: 1342–1351.

    Barber D. , 'Bayesian classification with Gaussian processes ' (1998 ) 20 IEEE Transactions on Pattern Analysis and Machine Intelligence : 1342 -1351.

    • Search Google Scholar
  • Zaniewski, A.E., A. Lehmann and J. Overton. 2002. Predicting species spatial distributions using presence-only data: a case study of native New Zealand ferns. Ecol. Model. 157: 261–280.

    Overton J. , 'Predicting species spatial distributions using presence-only data: a case study of native New Zealand ferns ' (2002 ) 157 Ecol. Model. : 261 -280.

    • Search Google Scholar