Application of Generalized Additive Model and Classification and Regression Tree to Estimate Potential Habitat Distribution of Range plant species (Case Study: Khazri Rangelands of Beyaz Plain, Southern Khorasan) | ||
| تحقیقات مرتع و بیابان ایران | ||
| Article 13, Volume 27, Issue 3 - Serial Number 80, October 2020, Pages 561-576 PDF (1.3 M) | ||
| Document Type: Research Paper | ||
| DOI: 10.22092/ijrdr.2020.342106.1947 | ||
| Authors | ||
| Maliheh Keyghobadi1; Hossein Piri Sahragard* 2; Mohammad Reza Pahlavan Rad3; Peyman Karami4; reza yari5 | ||
| 1Former M.Sc. Student in Range Management, Zabol University, Iran | ||
| 2Assistant Professor, Department of Rangeland and Watershed Management, Zabol University, Iran | ||
| 3Assistant professor, Soil and Water Research Department, Golestan Agricultural and Natural Resources Research and Education Center, AREEO, Gorgan, Iran | ||
| 4PhD student, Department of Environmental Sciences, Faculty of Natural Resources and the Environment Sciences, Malayer University, Malayer, Iran | ||
| 5Assistant Professor, rangeland science, Gorgan University of Agricultural Sciences and Natural Resources, Iran | ||
| Abstract | ||
| Species distribution models (SDMs) are the basis of informed decisions in vegetation management by quantifying the relationship between species distribution and influential environmental variables. The present study aimed to evaluate the GAM and CART models' performance in estimating the potential habitat distribution as well as recognizing the ecological needs of plant species in the Khezri rangelands of Bayaz plain of southern Khorasan. According to the regional condition and field observation, in an area of about 14500 hectares, vegetation sampling was done using the randomized-systematic method. Eighteen environmental variables including land characteristics, Normalized Difference Vegetation Index (NDVI), and salinity index were used as an estimator to generate maps of predictor variables. After modeling the habitat distribution prediction using CART and GAM methods in R 3.5.2 software, the accuracy of the models was assessed using the subsurface area (AUC) statistics. After determining the threshold by the TSS method, the continuous utility map was converted to the presence/absence map and the degree of conformity of the maps with the kappa index was calculated. Based on the results of the used models, the variables of the base level of the channels network, the vertical distance to the channels network, the depth of the valley, the wetness index, and the relative position of the slope are effective in habitat suitability for species establishment. In general, the GAM method has high accuracy in estimating the habitat distribution range of all species studied (Kappa≥ 0.9). According to the maps obtained from the GAM model, the highest and lowest potential habitats belong to S. rigida and T. serotina species. Therefore, the GAM method can be useful in accurately identifying the ecological needs of plant species and therefore their distribution useful at the local scale. As a result, it is suggested that this method be used as part of a management support system in the protection and restoration of vegetation in the rangelands of the Bayaz plain. | ||
| Keywords | ||
| Rangeland; Potential habitat; Machine learning models; Khezri rangelands | ||
| References | ||
|
- Aertsen, W., Kint, J. V. and Muys, B., 2010. Comparison and ranking of different modelling techniques for prediction of site index in Mediterranean mountain forests. Journal of Ecological Modelling, 221: 1119-1130. - Araujo, M. B. and New, M., 2007.Ensemble forecasting of species distributions. Journal of Trends in Ecology and Evolution, 22: 42-47. - Austin, M. P., Belbin, L., Meyers, J. A., Doherty, M. D. and Luoto, M., 2006. Evaluation of statistical models used for predicting plant species distributions: role of artificial data and theory. Journal of Ecological Modelling, 199:197-216. - Band, L.E., Hwang, T., Hales, T.C., Vose, J. and Ford, C., 2012. Ecosystem processes at the watershed scale: Mapping and modeling ecohydrological controls of landslides. Journal of Geomorphology, 137: 159-167. - Benito Garozn, M., Blazek, R., Neteler, M., Sanchez de Dios, R., Sainz Ollero, H. and Furlanello, C., 2006. Predicting habitat suitability with machine learning models: The potential area of Pinus sylvestris L. in the Iberian Peninsula. Journal of Ecological Modelling, 197: 383-393. - Ebrahimi, M., Masoodipour, A. and Rigi, M., 2015. Role of soil and topographic features in distribution of plant species (Case study: Sanib Taftan watershed). Journal of Ecopersia, 3: 917-932. - Esfandiary, F. and Dallal, O.A., 2018. Study the role of geomorphologic parameters in distribution of vegetation cover using spatial regression analysis (Case study, Arsbaran catchments: naposhtehcay, ilghinehcay and mardanqumcay). Journal of Geographic space,18 (63):225 -248. - Esfanjani, J., Zare Chahouki, M. A., Rouhani, H., Esmaeili, M. M. and Behmanesh, B., 2017. Suitibility habitat modeling species using Ecological Niche Factor Analysis (ENFA) in rangelands Chaharbagh of Golestan province, Iran. Iranian Journal of Range and Desert Research. 23(3): 516-526. - Fielding, A. H. and Bell, J. F., 1997. A review of methods for the assessment of prediction errors in conservation presence/absence models. Journal of Environmental Conservation, 24: 38-49. - Franklin, J., 2010. Mapping species distributions: spatial inference and prediction. Cambridge University Press. - Freeman, E. A. and Moisen, G. G., 2008. A comparison of the performance of threshold criteria for binary classification in terms of predicted prevalence and kappa. Journal of Ecological Modeling, 217: 48-58. - Fürnkranz, J., Gamberger, D. and Lavrač, N., 2012. Foundations of rule learning. Springer Science & Business Media, 233 p. - Ghazimoradi , M., Tarkesh, M., Bashari, H. and Vahabi, M. R., 2016. Determining the potential habitat of Ferula ovina (Boiss) using generalized additive model in Fereidonshahr rangelands, Isfahan. Journal of Range and Watershed Management, 69(3): 677-689. - Guisan, A. and Thuiller, W., 2005. Predicting species distribution: offering more than simple habitat models. Journal of Ecology Letters, 8(9): 993-1009. - Guisan, A., Tingley, R., Baumgartner, J. B., Naujokaitis., Lewis, I., Sutcliffe, P. R., Tulloch, A.I., Regan, T. J., Brotons, L., McDonald‐Madden, E., Mantyka‐Pringle, C. and Martin, T. G., 2013. Predicting species distributions for conservation decisions. Journal of Ecology letters, 16(12): 1424-1435. - Hastie, T. and Tibshirani, R., 1990. Exploring the nature of covariate effects in the proportional hazards model. Journal of Biometrics, 1005-1016. - Hosseini, S. Z., Kappas M., Zare Chahouki M. A., Gerold G., Erasmi S. and Rafiei Emam A., 2013. Modelling potential habitats for Artemisia sieberi and Artemisia aucheri in Poshtkouh area, central Iran using the maximum entropy model and geostatistics. Journal of Ecological Informatics, 18: 61-68. - Jafarian, Z. and Kargar, M., 2017. Distribution modeling of protective and valuable plant species in the tourist area of Polour using generalized linear model (GLM) and generalized additive model (GAM). Geography and Development Iranian Journal, 46: 117- 132. - Karami, P. and Mirsanjari, M., 2017. Modeling and identification of effective factors on the establishment of ecotourism in Javanrud County by using classification tree. Journal of Sustainability. Journal of Development and Environment, 4 (2):61-74. - Kargar, M., Jafarian, Z., Tamartash, R. and Alavi, S.J., 2017. Comparison of non-parametric and parametric species distribution models (SDM) in determining the habitat of dominant rangeland species (Case study: Khetteh Riz Rangelands). Iranian Journal of Range and Desert Research, 25 (3): 512-523. - Khalasi Ahvazi, L., Zare Chahouki, M. A. and 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. Journal of Rangeland Science, 3(1): 45-57. - Loh, W.Y., 2011. Classification and regression trees. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 1(1): 14-23. - Luca, C., Si, B.C. and Farrell, R.E., 2007 .Upslope length improves spatial estimation of soil organic carbon content. Canada Journal of Soil Science, (87) 1: 291-300. - Manel, S., Williams, H.C. and Ormerod, S.J., 2001. Evaluating presences-absence models in ecology: the need to account for prevalence. Journal of Applied Ecology, 38: 921-931. - McCullagh, P. and Nelder, J. A., 1989. Generalized Linear Models, Monographs on Statistics and Applied Probability, 2 edn, Chapman and Hall, London. - Miller, J. and Franklin, J., 2002. Modeling the distribution of four vegetation alliances using generalized linear models and classification trees with spatial dependence. Journal of Ecological modeling, 157(2-3): 227-247. - Mirakzehi, K. H., Shahriyari, L., Pahlavan Rad, M. R. and Bameri, A., 2015. Application random forest method in prediction of soil classes in low elevation (Case study: Hirmand Region). Journal of Soil and water conservation Research, 4(1): 69. - Monserud, R. A. and Leemans, R., 1992. Comparing global vegetation maps with the Kappa statistic. Journal of Ecological Modelling, 62: 275-293. - Mossivand, A. M., Ghorbani, A., Zare Chahoki, M. A., Keivan Behjou, F. and Sefidi, k., 2018. Environmental factors affecting the distribution of Prangos uloptera in rangelands of Ardabil Province. Iranian Journal of Range and Desert Research, 24 (4): 792-804. - Nodehi, N., Akbarlou, M., Sepehry, A. and Vahid, H., 2014. Effects of topographical factors on distribution of plant communities in semi-steppe grasslands (Case study: Ghorkhud Region, Northern Khorasan Province, Iran). Journal of Rangeland Science, 4(4): 298-305. - Pakgohar, A., 2016. Performance comparison of logistic regression and classification regression tree models for binary dependent variable. Journal of Statistical Sciences Extension, 1(2): 7-14. - Peterson, A. T., Soberón, J., Pearson, R. G., Anderson, R. P., Martínez-Meyer, E., Nakamura, M. and Araújo, M. B., 2011. Ecological niches and geographic distributions (MPB-49). Princeton University Press. - Pham, H., Guan, M. Y., Zoph, B., Le, Q. V. and Dean, J., 2018. Efficient neural architecture search via parameter sharing. arXiv preprint:1802.03268. - Piri Sahragard, H. and 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. - Piri Sahragard, H. and Piri, J., 2016. An estimation of spatial distribution domain of plant species using artificial neural networks in west rangelands of Taftan. Desert Ecosystem Engineering Journal (DEEJ), 12 (5): 23-36. - Piri Sahragard, H. and Zare Chahouki, M.A., 2016. Comparison of logistic regression and machine learning techniques in prediction of habitat distribution of plant species. Range Management and Agroforestry, 37 (1): 21-26. - Salehi, M., Vazirinasab, H., Khoshgam, M. and Rafati, N., 2012. Application of the generalized additive model in determination of the retinopathy risk factors relation types for Tehran diabetic patients. Razi Journal of Medical Sciences, 19(97): 1-9. - Sauer, T. and Ries, J. B., 2008. Vegetation cover and geomorpho dynamics on abandoned fields in the central Ebro Basin (Spain). Journal of Geomorphology, 102(2): 267-277. - Sutton, C.D., 2005. Classification and regression trees, bagging, and boosting. In: Rao C R, Wegman E J, Solka JL (eds) Handbook of statistics: data mining and data visualization, 24. Elsevier, Amsterdam. - Swets, J.A., 1988. Measuring the accuracy of a diagnostic systems. Journal of Science, 240, 1285-1293. - Tarkesh, M. and Jetshcke, G., 2012. Comparison of six correlative models in predictive vegetation mapping on a local scale. Journal of Environmental and Ecological statistics, 19(3): 437-457. - Tavakoli Neko, H., Pourmeydani, A., Adnani, S. M., and Sagheb-Talebi, K.H., 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. - Wieling, M., 2018. Analyzing dynamic phonetic data using generalized additive mixed modeling: a tutorial focusing on articulatory differences between L1 and L2 speakers of English. Journal of Phonetics, 70: 86-116. - Yee, T.W. and Mitchell, N.D., 1991. Generalized additive models in plant ecology. Journal of Vegetation Science, 2: 587-602. - Zare Chahouki, M. A., Khalasi Ahvazi, L. and Azarnivand, H., 2014. Plant species distribution modeling using logistic regression models in the north east of Semnan. Journal of Range and Watershed Management, 67(1): 45-59. - Zare Chahouki, M. A. and Piri Sahragard, H., 2016. Maxent modelling for distribution of plant species habitats of rangelands (Iran). Polish journal of ecology, 64 (4): 453-467.
| ||
|
Statistics Article View: 1,397 PDF Download: 800 |
||
Journal management system. designed by sinaweb