Evaluating Ecological Niche Models: A Comparison Between Maxent and GARP for Predicting Distribution of Hevea brasiliensis in India

  • Debabrata Ray
  • Mukunda Dev Behera
  • James Jacob
Research Article


Selection of appropriate ecological niche model for predicting species niche distribution has been a challenge considering the type of species and input variables. Therefore, two ecological niche modelling approaches (Maxent and GARP) are employed to predict the present distribution of a planted species (Hevea brasiliensis Muell. Arg.) in two bio-geographical regions of India: Western Ghats (WG) and North east (NE) regions. The difference between two approaches is in the algorithm and kinds of species data (presence-only or presence and absence) used for model training. GARP over-estimates were observed more in NE as compared to that of WG. Maxent predicts Hevea distribution more accurately in both regions as it considers presence-only data, which appears to be more accurate for this species. The over-prediction of Hevea niche distribution by GARP especially in NE may be attributed to inaccurate and insufficient ‘absence data’ as compared to ‘presence data’. The model accuracy estimator, AUC failed to attribute the difference in model predictability between Maxent and GARP, whereas partial-AUC is found to be better estimator of model spatial accuracy. Therefore, Maxent is found to be more appropriate model for predicting the niche distribution of a plantation species like Hevea.


Rubber tree Western Ghats Northeast India Regional suitability Species distribution model 



The authors are thankful to the Rubber Board and Indian Institute of Technology Kharagpur for permitting to conduct this research work. One of the author would like to thank the Rubber Board, Government of India, for sanctioning his study leave for conducting his PhD research at Indian Institute of Technology, Kharagpur. They appreciate the supports rendered by the officers of extension department of the Rubber Board during the field visits. They also declare that there is no conflict of interest among the authors in publishing this research work.


  1. 1.
    Massot M, Clobert J, Ferrière R (2008) Climate warming, dispersal inhibition and extinction risk. Glob Change Biol 14(3):461–469. doi: 10.1111/j.1365-2486.2007.01514.x CrossRefGoogle Scholar
  2. 2.
    Vos CC, Berry P, Opdam P et al (2008) Adapting landscapes to climate change: examples of climate-proof ecosystem networks and priority adaptation zones. J Appl Ecol 45(6):1722–1731. doi: 10.1111/j.1365-2664.2008.01569.x CrossRefGoogle Scholar
  3. 3.
    Hutchinson GE (1957) Concluding remarks. Cold Spring Harb Symp Quant Biol 22:415–427. doi: 10.1101/SQB.1957.022.01.039 CrossRefGoogle Scholar
  4. 4.
    Beaumont LJ, Hughes L (2002) Potential changes in the distributions of latitudinally restricted Australian butterfly species in response to climate change. Glob Change Biol 8(10):954–971. doi: 10.1046/j.1365-2486.2002.00490.x CrossRefGoogle Scholar
  5. 5.
    McCullagh P, Nelder JA (1989) Generalized linear models. In: Smith (ed) Monographs on statistics and applied probability, 2nd edn. Chapman & Hall/CRCGoogle Scholar
  6. 6.
    Fitzpatrick MC, Gove AD, Sanders NJ, Dunn RR (2008) Climate change, Plant migration, and range collapse in global biodiversity hotspot: the Banksia (Proteaceae) of Western Australia. Glob Change Biol 16(6):1337–1352. doi: 10.1111/j.1365-2486.2008.01559.x CrossRefGoogle Scholar
  7. 7.
    Phillips SJ, Anderson RP, Schapire RE (2006) Maximum entropy modelling of species geographic distributions. Ecol Model 190(3):231–259CrossRefGoogle Scholar
  8. 8.
    Guisan A, Zimmermann NE (2000) Predictive habitat distribution models in ecology. Ecol Model 135(2):147–186CrossRefGoogle Scholar
  9. 9.
    Strubbe D, Broennimann O, Chiron F, Matthysen E (2013) Niche conservatism in non-native birds in Europe: niche unfilling rather than niche expansion. Glob Ecol Biogeogr 22(8):962–970. doi: 10.1111/geb.12050 CrossRefGoogle Scholar
  10. 10.
    Evans JM, Fletcher RJ, Alavalapati J (2010) Using species distribution models to identify suitable areas for biofuel feedstock production. GCB Bioenergy 2(2):63–78. doi: 10.1111/j.1757-1707.2010.01040.x/ CrossRefGoogle Scholar
  11. 11.
    Ray D, Behera MD, Jacob J (2016) Predicting the distribution of rubber trees (Hevea brasiliensis)through ecological niche modelling with climate, soil, topography and socioeconomic factors. Ecol Res 31(1):75–91. doi: 10.1007/s11284-015-1318-7 CrossRefGoogle Scholar
  12. 12.
    Warren DL, Seifert SN (2010) Environmental niche modelling in Maxent: the importance of model complexity and the performance of model selection criteria. Ecol Appl 21(2):335–342. doi: 10.1890/10-1171.1 CrossRefGoogle Scholar
  13. 13.
    Stockwell DRB (1999) Genetic algorithms II. In: Fielding AH (ed) Machine learning methods for ecological applications. Kluwer Academic Publishers, Boston, pp 123–144CrossRefGoogle Scholar
  14. 14.
    Slater H, Michael E (2012) Predicting the current and future potential distributions of lymphatic filariasis in africa using maximum entropy ecological niche modelling. PLoS ONE 7(2):236–248. doi: 10.1371/journal.pone.0032202 CrossRefGoogle Scholar
  15. 15.
    Phillips SJ, Dudik M (2008) Modelling of species distributions with Maxent: new extensions and a comprehensive evaluation. Ecography 31(2):161–175. doi: 10.1111/j.0906-7590.2008.5203.x CrossRefGoogle Scholar
  16. 16.
    Fielding AH, Bell JF (1997) A review of methods for the measurement of prediction errors in conservation presence/absence models. Environ Conserv 24(1):38–49CrossRefGoogle Scholar
  17. 17.
    Lobo JM, Jiménez-Valverde A, Real R (2008) AUC: a misleading measure of the performance of predictive distribution models. Glob Ecol Biogr 17(2):145–151. doi: 10.1111/j.1466-8238.2007.00358.x CrossRefGoogle Scholar
  18. 18.
    Barve N (2008) Tool for Partial-ROC. Version 1. Lawrence, KS: Biodiversity Institute.
  19. 19.
    Indian Rubber Statistic (2014) Statistics and Planning Department. The Rubber Board, Kerela, Ministry of Commerce and Industry. Government of India, vol 36, pp 8–9Google Scholar
  20. 20.
    Ray D, Behera MD, Jacob J (2014) Indian Brahmaputra valley offers significant potential for cultivation of rubber trees under changed climate. Curr Sci 107(3):461–469Google Scholar
  21. 21.
    Nair NU, Nair KM, Meti SM, Rao DVKN, Chandy B, Naidu LGK (2010) Land and soil controls over the spatial distribution and productivity of rubber (Hevea brasiliensis) in Southern India. In: 19th World congress of soil science: soil solution for a changing world, 1–6 August, 2010, Brisbane, Australia.
  22. 22.
    Stockman AK, Beamer DA, Bond DA (2006) An evaluation of a GARP model as an approach to predicting the spatial distribution of non-vagile invertebrate species. Divers Distrib 12:81–89. doi: 10.1111/j.1366-9516.2006.00225.x CrossRefGoogle Scholar
  23. 23.
    Wang XY, Huang XL, Jiang LY, Qiao GX (2010) Predicting potential distribution of chestnut phylloxerid (Hemiptera: Phylloxeridae) based on GARP and Maxent ecological niche models. J Appl Entomol 134(1):45–54. doi: 10.1111/j.1439-0418.2009.01447.x CrossRefGoogle Scholar
  24. 24.
    Fernandez PA, Graham CH, Master LL, Albert DL (2006) The effect of sample size and species characteristics on performance of different species distribution modelling methods. Ecography 29:773–785CrossRefGoogle Scholar

Copyright information

© The National Academy of Sciences, India 2017

Authors and Affiliations

  • Debabrata Ray
    • 1
    • 2
  • Mukunda Dev Behera
    • 2
  • James Jacob
    • 3
  1. 1.Regional Research StationRubber Research Institute of IndiaAgartalaIndia
  2. 2.Centre for Oceans, Rivers, Atmosphere and Land SciencesIndian Institute of Technology KharagpurKharagpurIndia
  3. 3.Rubber Research Institute of IndiaKottayamIndia

Personalised recommendations