Advertisement

Contemporary Problems of Ecology

, Volume 11, Issue 6, pp 687–696 | Cite as

A Statistical Comparison between Less and Common Applied Models to Estimate Geographical Distribution of Endangered Species (Felis margarita) in Central Iran

  • Shiva TorabianEmail author
  • Mehrdad Ranaei
  • Saeid Pourmanafi
  • Laurie Chisholm
Article
  • 21 Downloads

Abstract

Species distribution in space is important in habitat conservation and biodiversity protection, so gaining knowledge about species range would be worthwhile to rescue endangered species and plan conservation policy. This study evaluates and compares the performance of an array of Species Distribution Models (SDMs), namely RF, SVM, MaxEnt, GLMNET, and MARS, in predicting rare sand cat distribution across a large unprotected sand dune area in central Iran. Due to absence of reliable data and difficulties in recording the species itself, the SDMs were challenged by limited data including 55 absence (background) and 40 presence points as well as nine climatic and geological parameters that influence on species distribution, including humidity, maximum, minimum and mean temperature, precipitation, amount of sunshine, ground water level, aspect, and DEM. Moreover, each model was replicated 20 times and the statistics including TSS, AUC, COR and Deviance were computed. Then, based on computed statistics, the model performances were evaluated by TUKEY and ANOVA. Finally, ensemble map was obtained by weighted approach using AUC. The results of this study showed that complex machine learning methods, like SVM, RF, and MaxEnt are more outperformed to predict the distribution of rare species.

Keywords

species distribution model sand cat Iran 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ahmadlou, M., Delavar, M.R., and Tayyebi, A., Comparing ANN and CART to model multiple land use changes: a case study of Sari and Ghaem–Shahr cities in Iran, J. Geomatics Sci. Technol., 2016, vol. 6, no. 1, pp. 292–303.Google Scholar
  2. Allouche, O., Tsoar, A., and Kadmon, R., Assessing the accuracy of species distribution models: prevalence kappa and the true skill statistic (TSS), J. Appl. Ecol., 2006, vol. 43, no. 6, pp. 1223–1232.CrossRefGoogle Scholar
  3. Amaral, S., Costa, C.B., and Renno, C.D., Normalized Difference Vegetation Index (NDVI) improving species distribution models: an example with the neotropical genus Coccocypselum (Rubiaceae), Anais XIII Simp. Brasileiro de Sensoriamento Remoto, Sao Paolo: Inst. Nacl. Pesquisas Espaciais, 2007, pp. 2275–2282.Google Scholar
  4. Araujo, M.B. and New, M., Ensemble forecasting of species distributions, Trends Ecol. Evol., 2007, vol. 22, no. 1, pp. 42–47.CrossRefGoogle Scholar
  5. Austin, M., Species distribution models and ecological theory: a critical assessment and some possible new approaches, Ecol. Model., 2007, vol. 200, no. 1, pp. 1–19.CrossRefGoogle Scholar
  6. Breiman, L., Statistical modeling: The two cultures (with comments and a rejoinder by the author), Stat. Sci., 2001a, vol. 16, no. 3, pp. 199–231.CrossRefGoogle Scholar
  7. Breiman, L., Random forests, Mach. Learn., 2001b, vol. 45, p. 5. https://doi.org/10.1023/A:1010933404324. CrossRefGoogle Scholar
  8. Bunaian, F., Mashaqbeh, S., Yousef, M., Buduri, A., and Amr, Z.S., A new record of the sand cat Felis margarita from Jordan, Zool. Middle East, 1998, vol. 16, no. 1, pp. 5–7.CrossRefGoogle Scholar
  9. Cunningham, P., Status of the sand cat Felis margarita in the United Arab Emirates, Zool. Middle East, 2002. 25, no. 1, pp. 9–14.CrossRefGoogle Scholar
  10. Cutler, D.R., Edwards, T.C., Beard, K.H., Cutler, A., Hess, K.T., Gibson, J., and Lawler, J.J., Random forests for classification in ecology, Ecology, 2007, vol. 88, pp. 2783–2792. doi 10.1890/07-0539.1CrossRefGoogle Scholar
  11. Dicko, A.H., Lancelot, R., Seck, M.T., Guerrini, L., Sall, B., Lo, M., Vreysen, M.J.B., Lefrancois, T., Fonta, W.M., Peck, S.L., and Bouyer, J., Using species distribution models to optimize vector control in the framework of the tsetse eradication campaign in Senegal, Proc. Natl. Acad. Sci. U.S.A., 2014, vol. 111, no. 28, pp. 10149–10154.CrossRefGoogle Scholar
  12. Douglas, M.W., Beida, R., Mejia, J.F., and Fuentes, M.V., Developing MODIS-based cloud climatologies to aid species distribution modeling and conservation activities, Front. Biogeogr., 2016, vol. 8, no. 3.Google Scholar
  13. Elith, J. and Leathwick, J.R., Species distribution models: ecological explanation and prediction across space and time, Ann. Rev. Ecol. Evol. Syst., 2009, vol. 40, pp. 677–697.CrossRefGoogle Scholar
  14. Eskildsen, A., Roux, P.C., Heikkinen, R.K., Hoye, T.T., Kissling, W.D., Poyry, J., Wisz, M.S., and Luoto, M., Testing species distribution models across space and time: high latitude butterflies and recent warming, Global Ecol. Biogeogr., 2013, vol. 22, no. 12, pp. 1293–1303.CrossRefGoogle Scholar
  15. Farber, O. and Kadmon, R., Assessment of alternative approaches for bioclimatic modeling with special emphasis on the Mahalanobis distance, Ecol. Model., 2003, vol. 160, no. 1, pp. 115–130.CrossRefGoogle Scholar
  16. Feuda, R., Bannikova, A.A., Zemlemerova, E.D., Febbraro, M.D., Loy, A., Hutterer, R., Aloise, G., Zykov, A.E., Annesi, F., and Colangelo, P., Tracing the evolutionary history of the mole, Talpa europaea through mitochondrial DNA phylogeography and species distribution modeling, Biol. J. Linn. Soc., 2015, vol. 114, no. 3, pp. 495–512.CrossRefGoogle Scholar
  17. Friedman, J.H., Multivariate adaptive regression splines, Ann. Stat., 1991, vol. 19, pp. 1–67.CrossRefGoogle Scholar
  18. Friedman, J., Hastie, T., and Tibshirani, R., Regularization paths for generalized linear models via coordinate descent, J. Stat. Software, 2008, vol. 33, no. 1, pp. 1–22.Google Scholar
  19. Fukuda, S., De Baets, B., Waegeman, W., Verwaeren, J., and Mouton, A.M., Habitat prediction and knowledge extraction for spawning European grayling (Thymallus thymallus L.) using a broad range of species distribution models, Environ. Model. Software, 2013, vol. 47, pp. 1–6.CrossRefGoogle Scholar
  20. Ghadirian, T., Akbari, H., Besmeli, M., Ghoddousi, A., Hamidi, A.Kh., and Dehkordi, M.E., Sand cat in Iran—present status, distribution, and conservation challenges, Cat News, 2016, vol. 10, pp. 56–59.Google Scholar
  21. Guisan, A. and Thuiller, W., Predicting species distribution: offering more than simple habitat models, Ecol. Lett., 2005, vol. 8, no. 9, pp. 993–1009.CrossRefGoogle Scholar
  22. Hannah, L., Midgley, G., Andelman, S., Araujo, M., Hughes, G., Martinez-Meyer, E., Pearson, R., and Williams, P., Protected area needs in a changing climate, Front. Ecol. Environ., 2007, vol. 5, no. 3, pp. 131–138.CrossRefGoogle Scholar
  23. Hardy, S.M., Lindgren, M., Konakanchi, H., and Huettmann, F., Predicting the distribution and ecological niche of unexploited snow crab (Chionoecetes opilio) populations in Alaskan waters: a first open-access ensemble model, Integr. Comp. Biol., 2011, vol. 51, no. 4, pp. 608–622.CrossRefGoogle Scholar
  24. Hemami, M.R., Ismaeeli, S., and Akbari, H., Dispersion and abundance of sand cat (Felis margarita) in Abbasabad wildlife refuge, National Conf. on Biodiversity of Iran, Tehran, 2010.Google Scholar
  25. Hemami, M.R., Esmaeili, S., and Akbari, H., Distribution and presence frequency of Sand Cat in Naein Twinship Isfahan Province, National Conf. of Desert Biomes, Isfahan Islamic Azad University, Najaf-Abad Branch, Tehran, 2013.Google Scholar
  26. Hernandez, P.A., Graham, C.H., Master, L.L., and Albert, D.L., The effect of sample size and species characteristics on performance of different species distribution modeling methods, Ecography, 2006, vol. 29, no. 5, pp. 773–785.CrossRefGoogle Scholar
  27. Hijmans, R.J. and Elith, J., Species Distribution Modeling with R, Vienna: R Found. Stat. Comput., 2017.Google Scholar
  28. JMP: Statistics and Graphics Guide, Cary, NC: SAS Inst., 2000.Google Scholar
  29. Karatzoglou, A., Meyer, D., and Hornik, K., Support vector machines in R, J. Stat. Software, 2006, vol. 15, no. 9.Google Scholar
  30. Klausmeyer, K.R. and Shaw, M.R., Climate change habitat loss protected areas and the climate adaptation potential of species in Mediterranean ecosystems worldwide, PloS One, 2009, vol. 4, no. 7, p. e6392.CrossRefGoogle Scholar
  31. Leathwick, J., Elith, J., and Hastie, T., Comparative performance of generalized additive models and multivariate adaptive regression splines for statistical modeling of species distributions, Ecol. Model., 2006, vol. 199, no. 2, pp. 188–196.CrossRefGoogle Scholar
  32. Mallon, D.P., Sliwa, A., and Srauss, M., Felis margarita, in The IUCN Red List of Threatened Species,https://www.iucnredlist.org. Glanz, 2011.Google Scholar
  33. Mateo, R.G., Croat, T.B., Felicisimo, A.M., and Munoz, J., Profile or group discriminative techniques? Generating reliable species distribution models using pseudoabsences and target-group absences from natural history collections, Diversity Distrib., 2010, vol. 16, no. 1, pp. 84–94.CrossRefGoogle Scholar
  34. Merow, C., Smith, M.J., and Silander, J.A., A practical guide to MaxEnt for modeling species’ distributions: what it does, and why inputs and settings matter, Ecography, 2013, vol. 36, no. 10, pp. 1058–1069.CrossRefGoogle Scholar
  35. Mi, C., Huettmann, F., Guo, Y., Han, X., and Wen, L., Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence, PeerJ, 2017, vol. 5, p. e2849.CrossRefGoogle Scholar
  36. Naimi, B. and Araújo, M.B., sdm: A reproducible and extensible R platform for species distribution modeling, Ecography, 2016, vol. 39, pp. 368–375.CrossRefGoogle Scholar
  37. Pearce, J. and Ferrier, S., An evaluation of alternative algorithms for fitting species distribution models using logistic regression, Ecol. Model., 2000, vol. 128, no. 2, pp. 127–147.CrossRefGoogle Scholar
  38. Phillips, S.J., Anderson, R.P., and Schapire, R.E., Maximum entropy modeling of species geographic distributions, Ecol. Model., 2006, vol. 190, no. 3, pp. 231–259.CrossRefGoogle Scholar
  39. Pohlert, T., The Pairwise Multiple Comparison of Mean Ranks Package (PMCMR), R Package, 2004–2006, Vienna: R Found. Stat. Comput., 2014.Google Scholar
  40. Reiss, H., Cunze, S., Konig, K., Neumann, H., and Kroncke, I., Species distribution modeling of marine benthos: a North Sea case study, Mar. Ecol.: Progr. Ser., 2011, vol. 442, pp. 71–86.CrossRefGoogle Scholar
  41. Shin, K.S., Lee, T.S., and Kim, H.J., An application of support vector machines in bankruptcy prediction model, Exp. Syst. Appl., 2005, vol. 28, no. 1, pp. 127–135.CrossRefGoogle Scholar
  42. Sliwa, A., Breton, G., and Chevalier, F., Sand cat sightings in the Moroccan Sahara, Cat News, 2013, vol. 59, pp. 28–30.Google Scholar
  43. Sliwa, A., Ghadirian, T., Appel, A., Banfield, L., Sher Shah, M., and Wacher, T., Felis margarita, in The IUCN Red List of Threatened Species, Glanz, 2016, no. eT8541A50651884.Google Scholar
  44. Václavík, T. and Meentemeyer, R.K., Invasive species distribution modeling (iSDM): Are absence data and dispersal constraints needed to predict actual distributions? Ecol. Model., 2009, vol. 220, no. 23, pp. 3248–3258.CrossRefGoogle Scholar
  45. Wisz, M.S., Hijmans, R., Li, J., Peterson, A.T., Graham, C., and Guisan, A., Effects of sample size on the performance of species distribution models, Diversity Distrib., 2008, vol. 14, no. 5, pp. 763–773.CrossRefGoogle Scholar

Copyright information

© Pleiades Publishing, Ltd. 2018

Authors and Affiliations

  • Shiva Torabian
    • 1
    Email author
  • Mehrdad Ranaei
    • 1
  • Saeid Pourmanafi
    • 1
  • Laurie Chisholm
    • 2
  1. 1.Department of Natural ResourcesIsfahan University of TechnologyIsfahanIran
  2. 2.School of Earth and Environmental SciencesUniversity of WollongongWollongong NSWAustralia

Personalised recommendations