Journal of Mountain Science

, Volume 15, Issue 10, pp 2159–2171 | Cite as

Modeling habitat suitability of range plant species using random forest method in arid mountainous rangelands

  • Hossein Piri SahragardEmail author
  • Majid Ajorlo
  • Peyman Karami


Mountainous rangelands play a pivotal role in providing forage resources for livestock, particularly in summer, and maintaining ecological balance. This study aimed to identify environmental variables affecting range plant species distribution, ecological analysis of the relationship between these variables and the distribution of plants, and to model and map the plant habitats suitability by the Random Forest Method (RFM) in rangelands of the Taftan Mountain, Sistan and Baluchestan Province, southeastern Iran. In order to determine the environmental variables and estimate the potential distribution of plant species, the presence points of plants were recorded by using systematic random sampling method (90 points of presence) and soils were sampled in 5 habitats by random method in 0–30 and 30–60 cm depths. The layers of environmental variables were prepared using the Kriging interpolation method and Geographic Information System facilities. The distribution of the plant habitats was finally modelled and mapped by the RFM. Continuous maps of the habitat suitability were converted to binary maps using Youden Index (J) in order to evaluate the accuracy of the RFM in estimation of the distribution of species potential habitat. Based on the values of the area under curve (AUC) statistics, accuracy of predictive models of all habitats was in good level. Investigating the agreement between the predicted map, generated by each model, and actual maps, generated from fieldmeasured data, of the plant habitats, was at a high level for all habitats, except for Amygdalus scoparia habitat. This study concluded that the RFM is a robust model to analyze the relationships between the distribution of plant species and environmental variables as well as to prepare potential distribution maps of plant habitats that are of higher priority for conservation on the local scale in arid mountainous rangelands.


Environmental (predictor) variables Habitat mapping Habitat distribution Random Forest Method Taftan Mountain 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.



This work was funded by University of Zabol, Iran (Grant No. UOZ-GR-9517-24). The authors would like to express their gratitude to the Vice Chancellery for Research and Technology, University of Zabol, for funding this study.

Supplementary material

11629_2018_4898_MOESM1_ESM.pdf (416 kb)
Modeling habitat suitability of range plant species using random forest method in arid mountainous rangelands


  1. Abd El–Ghani MM, Amer WM (2003) Soil vegetation relationships in coastal desert plain of southern Sinai, Egypt. Journal of Arid Environment 55: 607–628. CrossRefGoogle Scholar
  2. Ahmadi M, Nezami Balouchi B, Jowkar H, et al. (2017) Combining landscape suitability and habitat connectivity to conserve the last surviving population of cheetah in Asia. Diversity and Distributions 23(6): 592–603. CrossRefGoogle Scholar
  3. 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. CrossRefGoogle Scholar
  4. Arroita GG, Lahoz–Monfort J, Elith J, et al. (2015) Is my species distribution model fit for purpose? matching data and models to applications. Global Ecology and Biogeography 24: 276–292. CrossRefGoogle Scholar
  5. Azarnivand H, Jafari M, Moghaddam MR, et al. (2003) Investigation on environmental variables affecting habitat distribution of A. sieberi and A. aucheri in rangelands of Vardavard, Garmsar and Semnan–Iran. Journal of Natural Resources 56: 93–99. (In Persian) Benito Garzón M.BGoogle Scholar
  6. Blazek R, Neteler M, et al. (2006) Predicting habitat suitability with machine learning models: The potential area of Pinus sylvestris L. in the Iberian Peninsula. Ecological Modelling 197: 383–393. CrossRefGoogle Scholar
  7. Birks HJB (2012) Overview of numerical methods in palaeolimnology. In: Tracking Environmental Change Using Lake Sediments: Data Handling and Numerical Techniques. Springer Netherlands, pp. 19–92. CrossRefGoogle Scholar
  8. Breiman L (2001) Machine learning 45(1): 5–32.CrossRefGoogle Scholar
  9. Breiman L, Cutler A (2003) Random Forest Manual v4.0, Technical report, UC Berkeley. Available online at: ftp://ftp.stat. random forests v4.0.pdf (Accessed on 10 January 2018)Google Scholar
  10. Cheng L, Lek S, Lek–Ang S, et al. (2012) Predicting fish assemblages and diversity in shallow lakes in the Yangtze River basin. Limnologica–Ecology and Management of Inland Waters 42(2): 127–136. CrossRefGoogle Scholar
  11. Cutler DR, Edwards TC, Beard KH, et al. (2007) Random forests for classification in ecology. Ecology 88: 2783–2792. CrossRefGoogle Scholar
  12. Drew CA, Wiersma Y, Huettmann F (2011) Predictive species and habitat modeling in landscape ecology: concepts and applications. London: Springer. CrossRefGoogle Scholar
  13. Duan ZH, Xiao HL, Li XR et al. (2004) Evolution of soil properties on stabilized sands in the Tengger Desert, China. Geomorphology 59: 237–246. CrossRefGoogle Scholar
  14. Dubuis A, Pottier J, Rion V (2011) Predicting spatial patterns of plant species richness: a comparison of direct macro ecological and species stacking modelling approaches. Diversity and Distributions 17: 1122–1131. CrossRefGoogle Scholar
  15. Dubuis A, Giovanettina S, Pellisier L, et al. (2013) Improving the prediction of plant species distribution and community composition by adding edaphic to topo–climatic variable. Journal of Vegetation Science 24: 593–606. CrossRefGoogle Scholar
  16. Ebrahimi M, Masoudipour A, Rigi M (2015) Role of soil and topographic features in distribution of plant species (Case study: Sanib Taftan Watershed). Ecopersia 3 (1): 917–932.Google Scholar
  17. Ekhtesasi MR (2003) Determination of the minimum density of Haloxylon seedling in order to design tree windbreaks and wind erosion control in central Iran. Proceedings of national conference of the Haloxylon and planting of Haloxylon in Iran, Kerman. pp 2–3.Google Scholar
  18. Elith J, Leathwick JR (2009) The contribution of species distribution modelling to conservation prioritization. In: Moilanen A, Wilson KA, Possingham H (eds.), Spatial Conservation Prioritization: Quantitative Methods & Computational Tools. Oxford University Press. pp. 70–93Google Scholar
  19. Elith J, Graham CH, Anderson RP (2006) Novel methods improve prediction of species’ distributions from occurrence data. Ecography 29: 129–151.CrossRefGoogle Scholar
  20. Engler R, Guisan A, Rechsteiner L (2004) An improved approach for predicting the distribution of rare and endangered species from occurrence and pseudo–absence data. Journal of Applied Ecology 41: 263–274. CrossRefGoogle Scholar
  21. Evans J, Cushman S (2009) Gradient modeling of conifer species using random forests. Landscape Ecology 24: 673–683. CrossRefGoogle Scholar
  22. Fielding AH, Bell JF (1997) A review of methods for the assessment of prediction errors in conservation presence/absence models. Environmental Conservation 24: 38–49. CrossRefGoogle Scholar
  23. Franklin J (2013) Species distribution models in conservation biogeography: developments and challenges. Diversity Distribution 19: 1217–1223. CrossRefGoogle Scholar
  24. Freeman EA, Moisen GG (2008) A comparison of the performance of threshold criteria for binary classification in terms of predicted prevalence and kappa. Ecological Modeling 217: 48–58. CrossRefGoogle Scholar
  25. Gaston A, Garcia–Vinas JI (2011) Modelling species distributions with penalized logistic regressions: A comparison with maximum entropy models. Ecological Modelling 222: 2037–2041. CrossRefGoogle Scholar
  26. Ghimire B, Rogan J, Miller J (2010) Contextual land–cover classification: incorporating spatial dependence in land–cover classification models using random forests and the Getis statistic. Remote Sensing Letters 1(1): 45–54. CrossRefGoogle Scholar
  27. Ghorbanian D, Ghodrati M, Sharafieh H, et al. (2012) Comparison of cultivation and establishment of different xerophyte species for restoration and enhancement of vegetation in arid lands. Iranian Journal of Range and Desert Research 19(3): 443–456. (In Persian)Google Scholar
  28. Goudarzi GR, Sagheb–Talebi Kh, Ahmadloo F (2012) The study of effective factors on Almond (Amygdalus scoparia Spach.) distribation in Markazi province. Iranian Journal of Forest 4(3): 209–220.Google Scholar
  29. Guisan A, Thuiller W (2005) Predicting Species distribution: offering more than simple habitat models. Ecology Letter 8: 993–1009. HaidarianCrossRefGoogle Scholar
  30. Aghakhani M, Tamartash R, Jafarian Z, et al. (2017) Forecasts of climate change effects on Amygdalus scoparia potential distribution by using ensemble modeling in Central Zagros. RS & GIS for Natural Resources 8(3): 1–14. (In Persian)Google Scholar
  31. Heikkinen RK, Luoto M, Araújo MB, et al. (2006) Methods and uncertainties in bioclimatic envelope modelling under climate change. Progress in Physical Geography 30(6): 751–777. CrossRefGoogle Scholar
  32. Henderson EB, Ohmann JL, Gregory MJ, et al. (2014) Species distribution modelling for plant communities: stacked single species or multivariate modelling approaches? Applied Vegetation Science 17(3): 516–527. CrossRefGoogle Scholar
  33. Hengl T, Sierdsema H, Radovi A, Dilo A (2009) Spatial prediction of species’ distributions from occurrence–only records: combining point pattern analysis, ENFA and regression–kriging. Ecological Modelling 220 (24): 3499–3511. CrossRefGoogle Scholar
  34. Hosseini SZ, Kappas M, Zare Chahouki MA, et al. (2013) Modelling potential habitats for Artemisia sieberi and Artemisia aucheri in Poshtkouh area, central Iran using the maximum entropy model and geostatistics. Ecological Informatics 18: 61–68. CrossRefGoogle Scholar
  35. Jafarian Z, Kargar M (2017) Comparison of random forest (RF) and boosting regression tree (BRT) for prediction of dominant plant species presence in Plur rangelands, Mazandaran province, Iranian Journal of Applied Ecology 6(1): 41–55. Google Scholar
  36. Jianbing W, Boucher A, Zhang T (2008) A SGeMS code for pattern simulation of continuous and categorical variables: FILTERSIM. Computers & Geosciences 4(12): 1863–1876. Google Scholar
  37. Karami P, Mirsanjari M (2017) Modeling and identification of effective factors on the establishment of ecotourism in Javanrud County by using classification tree. Sustainability and Environment Quarterly 4(2): 61–74.Google Scholar
  38. Khalasi Ahvazi L, Zare Chahouki MA, Ghorbannezhad F (2012) Comparing discriminant analysis, ecological niche factor analysis and logistic regression methods for geographic distribution modelling of Eurotia ceratoides (L.) C. A. Mey. Rangeland Science 3: 45–57.Google Scholar
  39. Kikvidze Z, Pugnaire FI, Brooker RW, et al. (2005) Linking patterns and processes in alpine plant communities: a global study. Ecology 86: 1395–1400. CrossRefGoogle Scholar
  40. Lawson CR, Hodgson JA, Wilson RJ, et al. (2014) Prevalence, thresholds and the performance of presence–absence models. Methods in Ecology and Evolution 5: 54–64. CrossRefGoogle Scholar
  41. Liu C, Berry PM, Dawson TP, et al. (2005) Selecting thresholds of occurrence in the prediction of species distributions. Ecography 28: 385–393. CrossRefGoogle Scholar
  42. Liu C, White M, Newell G (2009) Measuring the accuracy of species distribution models: a review. In Proceedings 18th World IMACs/MODSIM Congress. Cairns, Australia 4241–4247.Google Scholar
  43. Lobo JM, Jimenez–Valverde A, Real R (2008) AUC: a misleading measure of the performance of predictive distribution models. Global Ecology and Biogeography 17: 145–151. CrossRefGoogle Scholar
  44. Mahmoodi E, Zahedi Amiri G, Etemad V (2012) Investigation of the Relationship between soil physiochemical properties and Haloxylon Vitality in natural and planted habitat of Haloxylon sp. (case study: Hossein Abad plain, Khorasan Jounobi Province). Journal of Iran Forest 4(4): 289–299. (In Persian)Google Scholar
  45. Mi C, Huettmann F, Guo Y, et al. (2017) Why choose Random Forest to predict rare species distribution with few samples in large under sampled areas? Three Asian crane species models provide supporting evidence. Peer J 5: e2849. Google Scholar
  46. Mohtashamnia S, Zahedi G, Arzani H (2011) Multivariate analysis of rangeland vegetation in relation to edaphical and physiographical factors. Procedia Environmental Sciences 7: 305–310. CrossRefGoogle Scholar
  47. Mokhtari K, Khajehdin J, Khademi H (2003) The relationship between the growth of the Haloxylon persicum and soil characteristics in Abu Zaidabad of Kashan, Proceedings of the National Conference on Haloxylon and planting of Haloxylon in Iran, Kerman. p 10. (In Persian)Google Scholar
  48. Monserud RA, Leemans R (1992) Comparing global vegetation maps with the Kappa statistic. Ecological Modelling 62: 275–293. CrossRefGoogle Scholar
  49. Pahlavan–Rad MR, Toomanian N, Khormali F, et al. (2014) Updating soil survey maps using random forest and conditioned latin hypercube sampling in the loess derived soils of northern Iran. Geoderma 232–234: 97–106. PiriCrossRefGoogle Scholar
  50. Sahragard H, Zare Chahouki MA (2015) An evaluation of predictive habitat models performance of plant species in Hozesoltan rangelands of Qom province. Ecological Modelling 309–310: 64–71. PiriCrossRefGoogle Scholar
  51. Sahragard H, Zare Chahouki MA, Ajorlo M, et al. (2016) Predictive habitat distribution map of Amygdalus scoparia spach in the Moshakieh rangelands of Qum Province. Journal of Forest and Wood Product 69 (4): 725–734. (In Persian) PiriGoogle Scholar
  52. Sahragard H, Ajorlo M, Sanchooli T (2017) Analysis of the relationship between rangeland vegetation types and environmental gradient using multivariate methods in western Taftan, southeastern Iran. Journal of Plant Ecosystem Conservation 4 (9): 97–114. (In Persian)Google Scholar
  53. Piri Sahragard H, Ajorlo M (2017) A comparison of logistic regression and maximum entropy for distribution modeling of range plant species (a case study in rangelands of western Taftan, southeastern Iran). Turkish Journal of Botany 41: 1–10. CrossRefGoogle Scholar
  54. Pottier J, Dubuis A, Pellissier L, et al. (2013) The accuracy of plant assemblage prediction from species distribution models varies along environmental gradients. Global Ecology and Biogeography 22: 52–63. CrossRefGoogle Scholar
  55. Rodriguez–Galiano V, Ghimire B, Rogan J, et al. (2012) An assessment of the effectiveness of a random forest classifier for land cover classification. ISPRS Journal of Photogrammetry and Remote Sensing. 67(1): 93–104.CrossRefGoogle Scholar
  56. Schroeder TA, Hamann A, Wang T (2010) Occurrence and dominance of six Pacific Northwest conifer species. Journal of Vegetation Science 21: 586–596.CrossRefGoogle Scholar
  57. Shataee SH, Kalb S, Fallah A, et al. (2012) Forest attribute imputation using machine–learning methods and ASTER data: Comparison of k–NN, SVR and random forest regression algorithms. International Journal of Remote Sensing 33: 6254–6280.CrossRefGoogle Scholar
  58. Sing T, Sander O, Beerenwinkel N et al. (2007) The ROCR Package. Technical Report. Available online at: (Accessed on 10 January 2018)Google Scholar
  59. Sweet JA (1988) Measuring the accuracy of diagnostic systems. Science 240: 1285–1293. CrossRefGoogle Scholar
  60. Syphard DA, Franklin J (2009) Differences in spatial predictions among species distribution modeling methods vary with species traits and environmental predictors. Ecography 32(6): 907–918. CrossRefGoogle Scholar
  61. Tarkesh M, Jetschke G (2012) Comparison of six correlative models in predictive vegetation mapping on a local scale. Environmental and Ecological Statistics 19: 437–457. TavakoliCrossRefGoogle Scholar
  62. Neko H, Pourmeydani A, Adnani SM, et al. (2012) Impact of some important ecological factors on presence of mountain Almond (Amygdalus scoparia Spach.) in Qom province, Iran. Iranian Journal of Forest and Poplar Research 19(4): 523–542. (In Persian)Google Scholar
  63. Unal I (2017) Defining an Optimal Cut–Point Value in ROC Analysis: An Alternative Approach. Computational and Mathematical Methods in Medicine 4: 1–14. CrossRefGoogle Scholar
  64. Youden W J (1950) Index for rating diagnostic tests. Cancer 3(1): 32–35.<32::aidcncr2820030106>;2-3 CrossRefGoogle Scholar
  65. Wilks DS (2011) Statistical methods in the atmospheric sciences. New York: Academic press.Google Scholar
  66. Wisz MS, Pottier J, Kissling WD, et al. (2013) The role of biotic interactions in shaping distributions and realized assemblages of species: implications for species distribution modelling. Biological Review 88: 15–30. Zare Chahouki M.ACrossRefGoogle Scholar
  67. Azarnivand H, Jafari M, et al. (2010) Multivariate statistical methods as a tool for model based prediction of vegetation. Russian Journal of Ecology 41(1): 84–94. CrossRefGoogle Scholar
  68. Chahouki MA, Khalasi Ahvazi L, Azarnivand H (2012) Comparison of three modeling approaches for predicting plant species distribution in mountainous scrub vegetation (Semnan rangelands, Iran). Polish Journal of Ecology 60(2): 105–117.Google Scholar
  69. Zare Chahouki MA, Piri Sahragard H (2016) MaxEnt modelling for distribution of plant species habitats of rangelands (Iran). Polish Journal of Ecology, 64 (4): 453–467. Google Scholar

Copyright information

© Science Press, Institute of Mountain Hazards and Environment, CAS and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Range and Watershed Management Department, Faculty of Soil and WaterUniversity of ZabolZabolIran
  2. 2.Department of Environmental Sciences, Faculty of Natural Resources and Environment SciencesMalayer UniversityMalayerIran

Personalised recommendations