Mapping spatial patterns of plant species based on machine-learning and regression models

Document Type : Research Paper

Authors

Department of Arid and Mountainous Regions Reclamation, Faculty of Natural Resources, University of Tehran, Karaj, Iran

Abstract

Various statistical techniques have been used for species distribution modeling that attempt to predict the occurrence of a given species with respect to environmental conditions. The current study was conducted to compare the performance of three regression-based models (multivariate adaptive regression splines, generalized additive models, and generalized linear models) with three machine-learning algorithms (random forest, artificial neural networks, and generalized boosted models). Also in this study, three sets of explanatory variables (climate-only, topography-only and combined topography-climate) for each species (i.e. Achillea millefolium, Festuca rupicola, and Centaurea jacea) were quantified and the effect of the interaction of the predictor variables with the modeling approaches on determining the accuracy of the predictions was tested. Model accuracy was evaluated using the area under the curve (AUC) of the receiver operating characteristics and true skill statistics (TSS). It was found that regression-based approaches, especially generalized additive model, performed better than those of machine-learning. The results showed that the topography-climate variables were the most important for mapping potentially suitable habitats of target species. The response curves associated with these variables indicate that there are ecological thresholds for favorable growth of all plant species studied.

Keywords


References Akaike H. 1998. A New Look at the Statistical Model Identification. In E. Parzen, K. Tanabe, and G.      Kitagawa (Eds.), Selected Papers of Hirotugu Akaike (pp. 215-222): Springer New York. Akhter S, Mcdonald MA, van Breugel P, Sohel S, Kjær ED, Mariott R. 2017. Habitat distribution modelling to identify areas of high conservation value under climate change for Mangifera sylvatica Roxb. of Bangladesh. Land Use policy, 60, 223–232. Al-Qaddi N, Vessella F, Stephan J, Al-Eisawi D, Schirone B. 2016. Current and future suitability areas of kermes oak (Quercus coccifera L.) in the Levant under climate change. Regional Environmental Change, 17, 143-156. Allouche O, Tsoar A, Kadmon, R. 2006. Assessing the accuracy of species distribution models: prevalence, kappa and the true skill statistic (TSS). Journal of Applied Ecology, 43, 1223-1232. Araujo MB, Guisan A. 2006. Five (or so) challenges for species distribution modelling. Journal of Biogeography, 33, 1677-1688. Austin MP. 2007. Species distribution models and ecological theory: a critical assessment and some possible new approaches, Ecological Modelling, 200, 1–19. Austin MP, Van Niel KP. 2011. Improving species distribution models for climate change studies: variable selection and scale. J Biogeogr, 38, 1–8. Balazy R, KamiƄska A, Ciesielski M, Socha J, Pierzchalski M. 2019. Modeling the Effect of Environmental and Topographic Variables Affecting the Height Increment of Norway Spruce Stands in Mountainous Conditions with the Use of LiDAR Data. Remote Sensing, 11 (20), 2407. Barbet-Massin M, Thuiller W, Jiguet F. 2012. The fate of European breeding birds under climate, land
179  Keshtkar & Poormohammad 
 
 
use and dispersal scenarios. Global Change Biology, 18, 881-890. Bateman BL, Murphy HT, Reside AE, Mokany K, VanDerWal J. 2013. Appropriateness of full-, partial- and no-dispersal scenarios in climate change impact modelling. Diversity and Distributions, 19, 12241234. Breiman L. 2001. Random Forests. Machine Learning, 45, 5-32. Bucklin DN, Basille M, Benscoter AM, Brandt LA, Mazzotti FJ, Romañach SS, Speroterra C, Watling J.I. 2015. Comparing species distribution models constructed with different subsets of environmental predictors. Diversity and Distributions, 21, 23-35. Cianci D, Hartemink N, Ibanez-Justicia A. 2015. Modelling the potential spatial distribution of mosquito species using three different techniques. International Journal of Health Geographics, 14, 10-20. Dirnböck T, Essl F, Rabitsch W. 2011. Disproportional risk for habitat loss of high-altitude endemic species under climate change. Global Change Biology, 17, 990-996. Duan RY, Kong XQ, Huang MY, Fan WY, Wang ZG. 2014. The predictive performance and stability of six species distribution models. PLoSOne, 9, e112764. Elith J, Leathwick J. 2009. species distribution models: ecological explanation and prediction across space and time. Annual Review of Ecology Evolution and Systematics, 40(1), 677-697. Engler R, Randin CF, Vittoz P, Czáka T, Beniston M, Zimmermann NE, Guisan A. 2009. Predicting future distributions of mountain plants under climate change: does dispersal capacity matter? Ecography, 32, 34-45. Eskildsen A, Roux PC, Heikkinen RK, Høye TT, Kissling WD, Pöyry J, Wisz MS, Luoto M. 2013. Testing species distribution models across space and time: high latitude butterflies and recent warming. Global Ecology and Biogeography, 22(12), 1293–1303. Friedman J. 1991. Multivariate adaptive regression splines. Annals of Statistics, 19, 1–141. Franklin J. 2009. Mapping Species Distributions: Spatial Inference and Prediction. Cambridge: Cambridge University Press. Guisan A, Zimmermann NE, Elith J, Graham CH, Phillips S, Peterson AT. 2007. What Matters for Predicting the Occurrences of Trees: Techniques, Data, or Species' Characteristics? Ecological Monographs, 77, 615-630. Guisan A. 2013. Predicting species distributions for conservation decisions. Ecol. Lett. 16, 1424–1435. Hanley JA, McNeil BJ. 1982. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 143, 29-36. Hastie TJ, Tibshirani RJ. 1990. Generalized Additive Models. New York: Chapman and Hall. Heikkinen RK, Marmion M, Luoto M. 2012. Does the interpolation accuracy of species distribution models come at the expense of transferability? Ecography, 35, 276-288. Holcombe TR, Stohlgren TJ, Jarnevich CS. 2010. From points to forecasts: predicting invasive species habitat suitability in the near term. Diversity, 2(5), 738–767. Huberty CJ. 1994. Applied Discriminant Analysis. New York: Wiley. Ibáñez I, Katz DS, Peltier D, Wolf SM, Connor Barrie BT. 2014. Assessing the integrated effects of landscape fragmentation on plants and plant communities: the challenge of multiprocess– multiresponse dynamics. Journal of Ecology, 102(4), 882-895. Isabelle B, Damien G, Wilfried T. 2014. FATE-HD: a spatially and temporally explicit integrated model for predicting vegetation structure and diversity at regional scale. Global Change Biology, 20, 23682378. Keshtkar H, Voigt W. 2016. Potential impacts of climate and landscape fragmentation changes on plant distributions: coupling multi-temporal satellite imagery with GIS-based cellular automata model. Ecological Informatics, 32, 145–155.  Kissling WD, Field R, Korntheuer H, Heyder U, Böhning-Gaese K. 2010. Woody plants and the prediction of climate-change impacts on bird diversity. Philosophical Transactions of the Royal Society B: Biological Sciences, 365, 2035-2045. Kosanic A, Anderson K, Harrison S, Turkington T, Bennie J. 2018. Changes in the geographical distribution of plant species and climatic variables on the West Cornwall peninsula (South West UK). PloS One, 13(2), e0191021. Kumar P. 2012. Assessment of impact of climate change on Rhododendrons in Sikkim Himalayas using Maxent modelling: limitations and challenges. Biodiversity and Conservation, 21, 1251-1266. Leathwick JR, Rowe D, Richardson J, Elith J, Hastie T. 2005. Using multivariate adaptive regression 
DESERT 2022, 27(1): 167-181                                                                                                                                                  180   
splines to predict the distributions of New Zealand's freshwater diadromous fish. Freshwater Biology, 50, 2034-2052. Lehmann A, Overton J McC, Austin MP. 2002. Regression models for spatial prediction: their role for biodiversity and conservation. Biodiversity and Conservation, 11, 2085–2092. Liu C, Berry PM, Dawson TP, Pearson RG. 2005. Selecting thresholds of occurrence in the prediction of species distributions. Ecography, 28, 385-393. McCullagh P, Nelder JA. 1989. Generalized Linear Models, Chapman and Hall, London. Naghipour AA, Teimoori Asl S, Ashrafzadeh MR, Haidarian M. 2021. Predicting the Potential Distribution of Crataegus azarolus L. under Climate Change in Central Zagros, Iran. Journal of Wildlife and Biodiversity, 5(4), 28-43. Naimi B, Araújo MB. 2016. sdm: A reproducible and extensible R platform for species distribution modelling. Ecography, 39(4), 368–375. Norberg A. 2019. A comprehensive evaluation of predictive performance of 33 species distribution models at species and community levels. Ecological Monographs, 89, 1–24. Oppel S, Meirinho A, Ramírez I, Gardner B, O’Connell AF, Miller PI, Louzao M. 2012. Comparison of five modelling techniques to predict the spatial distribution and abundance of seabirds. Biological Conservation, 156, 94-104. Parviainen M, Luoto M, Ryttäri T, Heikkinen RK. 2008. Modelling the occurrence of threatened plant species in taiga landscapes: methodological and ecological perspectives. Journal of Biogeography, 35, 1888-1905. Pearson RG, Dawson TP, Berry PM, Harrison PA. 2002. SPECIES: A Spatial Evaluation of Climate Impact on the Envelope of Species. Ecological Modelling, 154, 289-300. Phillips SJ, Dudik M, Elith J, Graham C, Lehmann A, Leathwick J. 2009. Sample selection bias and presence-only models of species distributions. Ecological Applications, 19, 181–197. R Core Team 2014. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL http://www.R-project.org/ Rafiee G, Jafari R, Matinkhah SH, Tarkesh isfahani M, karimzadeh HR, jafari Z. 2020. Predicting the Potential Habitat Distribution of Crataegus Pontica C. Koch, Using a Combined Modeling Approach in Lorestan Province. Ijae, 9(2), 45-59. Rajpoot R, Adhikari D, Verma S, Saikia P, Kumar A, Grant KR. 2020. Climate models predict a divergent future for the medicinal tree Boswellia serrata Roxb. In India. Global Ecology and Conservation, 23, e01040. Ridgeway G. 1999. “The state of boosting,” Computing Science and Statistics. 31, 172-181. Ripley BD. 1996. Pattern recognition and neural networks. Cambridge: Cambridge University Press. Robertson MP, Peter CI, Villet MH, Ripley BS. 2003. Comparing models for predicting species’ potential distributions: a case study using correlative and mechanistic predictive modelling techniques. Ecological Modelling, 164, 153-167. Sartz Richard S. 1972. Effect of topography on microclimate in southwestern Wisconsin. Research Paper NC-74. St. Paul, MN: U.S. Dept. of Agriculture, Forest Service, North Central Forest Experiment Station. Shrestha N. 2020. Detecting Multicollinearity in Regression Analysis. American Journal of Applied Mathematics and Statistics, 8, 39-42. Thuiller W, Georges D, Engler R, Araujo MB. 2013. biomod2: Ensemble platform for species distribution modelling. Ecography, 32, 369-373.  Thuiller W, Georges D, Engler R, Breiner F, Georges MD, Thuiller CW. 2016. Package ‘biomod2’. https://cran.r-project.org/package= biomod2. Xu Y, Huang Y, Zhao H, Yang M, Zhuang Y, Ye X. 2021. Modelling the Effects of Climate Change on the Distribution of Endangered Cypripedium japonicum in China. Forests. 12(4), 429. Wiens JA, Stralberg D, Jongsomjit D, Howell CA, Snyder MA. 2009. Niches, models, and climate change: Assessing the assumptions and uncertainties. Proceedings of the National Academy of Sciences of the United States of America, 106, 19729-19736. Wilson JP, Gallant JC. 2000. Terrain Analysis: Principles and Applications. Wiley. Zimmermann NE, Edwards TC, Graham CH, Pearman PB, Svenning JC. 2010. New trends in species distribution modelling. Ecography, 33, 985-989. Zimmermann NE, Kienast F. 1999. Predictive mapping of alpine grasslands in Switzerland: Species 
181  Keshtkar & Poormohammad 
 
 
versus community approach. Journal of Vegetation Science, 10, 469-482. Zomer RJ, Xu J, Wang M, Trabucco A, Li Z. 2015. Projected impact of climate change on the effectiveness of the existing protected area network for biodiversity conservation within Yunnan Province, China. Biological Conservation, 184, 335-345.