Journal of Korean Society for Geospatial Information Science (대한공간정보학회지)

Korea Spatial Information Society (대한공간정보학회)
권호 표지
DOI QR코드

DOI QR Code

Applying Ensemble Model for Identifying Uncertainty in the Species Distribution Models

종분포모형의 불확실성 확인을 위한 앙상블모형 적용

  • Received : 2014.08.22
  • Accepted : 2014.12.08
  • Published : 2014.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Species distribution models have been widely applied in order to assess biodiversity, design reserve, manage habitat and predict climate change. However, SDMs has been used restrictively to the public and policy sectors owing to model uncertainty. Recent studies on ensemble and consensus models have been increased to reduce model uncertainty. This paper was carried out single model and multi model for Corylopsis coreana and compares two models. First, model evaluation was used AUC, kappa and TSS. TSS was the most effective method because it was easy to compare several models and convert binary maps. Second, both single and ensemble model show good performance and RF, Maxent and GBM was evaluated higher, GAM and SRE was evaluated lower relatively. Third, ensemble model tended to overestimate over single model. This problem can be solved by the suitable model selection and weighting through collaboration between field experts and modeler. Finally, we should identify causes and magnitude of model uncertainty and improve data quality and model methods in order to apply special decision-making support system and conservation planning, and when we make policy decisions using SDMs, we should recognize uncertainty and risk.

종분포모형은 생물다양성 평가, 보호지역 지정, 서식지 관리 및 복원, 기후변화 예측 등의 다양한 분야에 활용되고 있으나 공공이나 정책분야에서는 모형의 불확실성으로 인하여 활용이 제한적이었다. 최근에는 이러한 모형의 불확실성을 저감하기 위하여 앙상블이나 합의모형 등의 다중모형을 적용하는 연구가 증가하고 있다. 이에 본 연구에서는 히어리를 대상으로 단일모형과 앙상블(다중) 모형을 적용하고 이를 비교하는 연구를 수행하였다. 모형은 AUC와 kappa, TSS를 이용하여 적합도를 평가하였으며, 이 중 모형 간의 비교가 용이하고 이항형 지도로 바로 변환할 수 있는 TSS가 효과적이었다. 단일모형과 앙상블 모형 모두 높은 모형적합도를 나타내었으며, 다중 모형 중에서는 RF, Maxent, GBM이 높게, GAM, SRE는 비교적 낮게 평가되었다. 예측지도에서는 단일모형에 비해 다중모형의 예측범위가 과대 추정되는 경향이 있었다. 이는 여러 모형이 중첩된 결과로 현장전문가와 모형전문가들 간의 협력연구를 통하여 적절한 모형 선택과 가중치 부여 등을 통하여 문제를 해결할 수 있다. 앙상블모형을 공간의사결정이나 보호지역계획에 활용하기 위해서는 불확실성의 정도와 원인을 파악하고, 이를 저감하려는 개선작업과 함께 결과의 불확실성이나 위험성을 인지하고 의사결정을 해야 한다.

Keywords

References

  1. Allouche, Omri, Asaf Tsoar, and Ronen Kadmon. 2006, Assessing the accuracy of species distribution models: prevalence, kappa and the True Skill Statistic (TSS), Journal of Applied Ecology, Vol.43, No.6, pp.1223-1232. https://doi.org/10.1111/j.1365-2664.2006.01214.x
  2. Araujo, M.B., R.J. Whittaker, R.J. Ladle and M. Erhard, 2005, Reducing uncertainty in projections of extinction risk from climate change. Global Ecology and Biogeography, Vol. 14, pp.529-538. https://doi.org/10.1111/j.1466-822X.2005.00182.x
  3. Barbet-Massin, M., F. Jiguet, C.H. Albert, and W. Thuiller, 2012, Selecting Pseudo-absences for species distribution models: how, where and how many?, Methods in Ecology and Evolution, Vol.3, No.2, pp.327-338. https://doi.org/10.1111/j.2041-210X.2011.00172.x
  4. Braunisch, V., J. Coppes, R. Arlettaz, R. Suchant, H. Schmid and K. Bollmann, 2013, Selecting from correlated climate variables: a major source of uncertainty for predicting species distributions under climate change. Ecography, Vol.36, No.1, pp.1-13. https://doi.org/10.1111/j.1600-0587.2012.07785.x
  5. Buisson, L., W. Thuiller, N. Casajus, S. Lek and G. Grenouillet, 2010, Uncertainty in ensemble forecasting of species distribution. Global Change Biology, Vol.16, No.4, pp.1145-1157 https://doi.org/10.1111/j.1365-2486.2009.02000.x
  6. Elith, J. and J.R. Leathwick, 2009, Species Distribution Models: Ecological explanation and prediction across space and time, Annual Review of Ecology, Evolution, and Systematics, Vol.40, No.1 pp.677-697. https://doi.org/10.1146/annurev.ecolsys.110308.120159
  7. Flather, C.H., K.R. Wilson, D.J. Dean and W.C. McComb, 1997, Identifying gaps in conservation networks : of indicators and uncertainty in geographic-based analyses. Ecological Applications, Vol.7, No.2, pp.531-542. https://doi.org/10.1890/1051-0761(1997)007[0531:IGICNO]2.0.CO;2
  8. Franklin, J., 2009. Mapping species distributions spatial inference and prediction, 1st ed., New York: Cambridge University Press.
  9. Jeon, S.W., J. Kim, H. Jung, W.K. Lee and J.S. Kim, 2014, Species distribution modeling of endangered mammals for ecosystem services valuation; focused on national ecosystem survey data, J. Korean Env. Res. Tech., Vol.17, No.1, pp.111-122. https://doi.org/10.13087/kosert.2014.17.1.111
  10. Kim, H., 2012, (A) study on the method establishing protected areas for the prediction of habitat distribution changes of living species by climate change : focused on forest vegetations, birds and amphibians, Master's thesis, Seoul National University.
  11. Kim, J., C. Seo, H. Kwon, J.E. Ryu, and M. Kim, 2012, A study on the species distribution modeling using national ecosystem survey data, Journal of Environmental Impact Assessment, Vol.21, No.4, pp.593-607.
  12. Kwon, H., 2011, Integrated evaluation model of biodiversity for conservation planning: focused on Mt. Jiri, Mt. Deokyu and Mt. Gaya regions, Doctoral dissertation, Seoul National University.
  13. Kwon, H., C. Seo and C. Park, 2012c, Development of species distribution models and evaluation of species richness in Jirisan region, Korean Society for Geospatial Information System, Vol.20, No.3, pp.11-18. https://doi.org/10.7319/kogsis.2012.20.3.011
  14. Kwon, H., J.E. Ryu, C. Seo, J. Kim, D.O. Lim and M.H. Suh, 2012a, A study on distribution characteristics of corylopsis coreana using SDM, Journal of Environmental Impact Assessment, Vol.21, No.5, pp.735-743.
  15. Kwon, H., J.E. Ryu, C. Seo, J. Kim, J. .Tho, M.H. Suh and C. Park, 2012b, Climatic and environmental effects on distribution of narrow range plants, Vol.15, No.6, pp.17-27. https://doi.org/10.13087/kosert.2012.15.6.017
  16. Latif, Q.S., V.A. Saab, J.G. Dudley and J.P. Hollenbeck, 2013, Ensemble modeling to predict habitat suitability for a large-scale disturbance specialist. Ecology and evolution, Vol.3 , No.13, pp.4348-4364. https://doi.org/10.1002/ece3.790
  17. Meller, L., M. Cabeza, S. Pironon, M. Barbet-Massin, L. Maiorano, D. Georges and W. Thuiller, 2014, Ensemble distribution models in conservation prioritization: from consensus predictions to consensus reserve networks, Diversity and Distributions Vol.20 pp.309-321. https://doi.org/10.1111/ddi.12162
  18. Rodder, D., J. Kielgast, J. Bielby, S. Schmidtlein, J. Bosch, T.W.J. Garner, M. Veith, S. Walker, M.C. Fisher and S. Lotters, 2009, Global amphibian extinction risk assessment for the Panzootic Chytrid Fungus, Diversity, Vol.1, pp.52-66. https://doi.org/10.3390/d1010052
  19. Seo, C., J.H. Thorne, L. Hannah and W. Thuiller, 2009, Scale Effects in species distribution models: implications for conservation planning under climate change, Biology Letters, Vol.5, No.1, pp.39-43. https://doi.org/10.1098/rsbl.2008.0476
  20. Song, W. and E. Kim, 2012, A comparison of machine learning species distribution methods for habitat analysis of the Korea water deer (Hydropotes inermis argyropus), Korean Journal of Remote Sensing, Vol.28, No.1, pp.171-180. https://doi.org/10.7780/kjrs.2012.28.1.171
  21. Thorn, J.S., V. Nijman, D. Smith and K.A.I. Nekaris, 2009, Ecological niche modelling as a technique for assessing threats and setting conservation priorities for Asian slow lorises (Primates: Nycticebus), Diversity and Distributions, Vol.15, No.2, pp.289-298. https://doi.org/10.1111/j.1472-4642.2008.00535.x
  22. Thuiller, W., B. Lafourcade, R. Engler and M.B. Araujo, 2009, BIOMOD - a platform for ensemble forecasting of species distributions, Ecography, Vol.32, No.3, pp.369-373. https://doi.org/10.1111/j.1600-0587.2008.05742.x
  23. Yun, J.H., K. Nakao, C.H. Park, B.Y. Lee and K.H. Oh, 2011, Change prediction for potential habitats of warm-temperate evergreen broad-leaved trees in Korea by climate change, Kor. J. Env. Eco., Vol. 25, No.4. pp.171-180.

Cited by

  1. Accuracy Evaluation of Potential Habitat Distribution in Pinus thunbergii using a Species Distribution Model: Verification of the Ensemble Methodology vol.11, pp.1, 2014, https://doi.org/10.15531/ksccr.2020.11.1.37