Investigation of a possibility of spatial modelling of tree diversity using environmental and data mining algorithms
A. Abdollahnejad, D. Panagiotidis, P. Surovýhttps://doi.org/10.17221/97/2016-JFSCitation:Abdollahnejad A., Panagiotidis D., Surový P. (2016): Investigation of a possibility of spatial modelling of tree diversity using environmental and data mining algorithms. J. For. Sci., 62: 562-570.
Biological diversity is the basis for a wide array of goods and services provided by forests. The variety of forest trees and shrubs plays a vital role in the daily life of forest communities. The purpose of this study is to investigate the possibility of modelling the diversity of tree species by characteristics of topography, soil and climate, using data mining algorithms k-NN, RF and SVM in Dr. Bahramnia forestry plan in the north of Iran. Based on the basal area factor for each species in a total of 518 sample plots, diversity indices such as species richness, evenness and heterogeneity were calculated for each plot. Topographic maps of primary and secondary properties were prepared using the digital elevation model. Categories of the soil and climate maps database of Dr. Bahramnia forestry plan were extracted. Modelling rates of tree and shrub species diversity using data mining algorithms, with 80% of the sampling plots were taken. Assessment of the model accuracy, using 20% of samples and evaluation criteria, was conducted. Results showed that topographic features, especially elevation, had the highest impact on the species diversity index. The modelling results also showed that Camargo evenness index had lowest root mean square error (RMSE) (0.14) and RMSE% (24.35), compared to other indicators of diversity. In addition, the results of the comparison between the algorithms showed that the random forest algorithms were more accurate in modelling the diversity.Keywords:
topographic characteristics; suborder soil; climate; non-parametric algorithms; richness; evenness indicatorsReferences:
Abdollahnejad A., Shataee S.H. (2014): The study of tree and shrub species diversity changes in the parameters of a physiographic, soil and vegetation. District one of DR. Bahramnia forestry plan. Journal of Wood and Forest Science and Technology, 21: 61–84. (in Persian)Ardestani E., Basir M., Torkesh M., Borhani M. (2010): Indicators for assessment of pasture species diversity in four places in Isfahan province. Journal of Rangeland, 4: 43–46. (in Persian)Bale C.L, Williams J.B, Charley J.L (1998): The impact of aspect on forest structure and floristics in some Eastern Australian sites. Forest Ecology and Management, 110, 363-377 https://doi.org/10.1016/S0378-1127(98)00300-4BEVEN K. J., KIRKBY M. J. (1979): A physically based, variable contributing area model of basin hydrology / Un modèle à base physique de zone d'appel variable de l'hydrologie du bassin versant. Hydrological Sciences Bulletin, 24, 43-69 https://doi.org/10.1080/02626667909491834Brutsaert Wilfried (1975): On a derivable formula for long-wave radiation from clear skies. Water Resources Research, 11, 742-744 https://doi.org/10.1029/WR011i005p00742Byroodyan M. (1990): Weather and Climatology (Ghare Sou River Watershed Studies). Gorgan, Agriculture Publication: 300. (in Persian)Camargo JulioA. (1992): New diversity index for assessing structural alterations in aquatic communities. Bulletin of Environmental Contamination and Toxicology, 48, - https://doi.org/10.1007/BF00195643Ejtehadi H., Sepehry A., Akafi H.R. (2010): Methods of Measuring Biodiversity. Mashhad, University of Mashhad: 288. (in Persian)Fallahchay M.M., Marvie Mohajer M.R. (2005): Ecological role of elevation on tree diversity of Siahkal forest in the north of Iran. Iranian Journal of Natural Resources, 58: 89–101. (in Persian)Franklin Janet (1998): Predicting the distribution of shrub species in southern California from climate and terrain-derived variables. Journal of Vegetation Science, 9, 733-748 https://doi.org/10.2307/3237291Ghanbari F. (2008): Predicting the spatial distribution of forest allometric growth properties using geostatistics and GIS. [MSc Thesis.] Gorgan, Gorgan University of Agricultural Sciences and Natural Resources: 160. (in Persian)Ghanbari F., Shataee S.H., Mohseni A., Habashi H. (2011): Using a logistic regression model to predict the spatial characteristics of topography and forest type. Iranian Journal of Forest and Poplar Research, 19: 27–41. (in Persian)Gixhari B., Ismaili H., Vrapi H., Elezi F., Dias S., Sulovari H. (2012): Geographic distribution and diversity of fruit tree species in Albania. International Journal of Ecosystems and Ecology Sciences, 2: 355–360.Gracia Marc, Montané Francesc, Piqué Josep, Retana Javier (2007): Overstory structure and topographic gradients determining diversity and abundance of understory shrub species in temperate forests in central Pyrenees (NE Spain). Forest Ecology and Management, 242, 391-397 https://doi.org/10.1016/j.foreco.2007.01.056Lan Guoyu, Hu Yuehua, Cao Min, Zhu Hua (2011): Topography related spatial distribution of dominant tree species in a tropical seasonal rain forest in China. Forest Ecology and Management, 262, 1507-1513 https://doi.org/10.1016/j.foreco.2011.06.052Ismail R., Mutanga O. (2010): A comparison of regression tree ensembles: Predicting Sirex noctilio induced water stress in Pinus patula forests of KwaZulu-Natal, South Africa. International Journal of Applied Earth Observation and Geoinformation, 12, S45-S51 https://doi.org/10.1016/j.jag.2009.09.004Ismailzadeh A., Hosseini M. (2007): Relationship between ecological groups of plants with biodiversity indicators of plants in Afratakhteh cache for Taxus bacata. Journal of Ecology, 43: 21–30. (in Persian)Kardgar N. (2012): Accuracy assessment of soil maps in Dr. Bahramnia forestry plan. [MSc Thesis.] Gorgan, Gorgan University of Agricultural Sciences and Natural Resources: 150. (in Persian)Kernes B.K., Ohmann J.L. (2004): Evaluation and prediction of shrub cover in coastal Oregon forests (USA). Catena, 55: 341–365.Kint V., van Meirvenne M., Nachtergale L., Geudens G., Lust N. (2003): Spatial methods for quantifying forest stand structures development: A comparison between nearest neighbour indices and variogram analysis. Forest Science, 49: 36–49.Krebs C.J. (1999): Ecological Methodology. 2nd Ed. Menlo Park, Addison-Welsey Educational Publishers, Inc.: 620.Kymasi F. (2012): Spatial distribution of tree and shrub species diversity in forests in Golestan province using GIS. [MSc Thesis.] Gorgan, Gorgan University of Agricultural Sciences and Natural Resources: 170. (in Persian)Ludwing J.A., Reynolds J.F. (1988): Statistical Ecology: A Primer on Methods and Computing. New York, John Wiley & Sons: 202.Maguran A.E. (1996): Ecological Diversity and Its Measurement. Princeton, Chapman & Hall: 179.Marvie Mohajer M.R. (2006): Silviculture. Tehran, Tehran University Press: 387. (in Persian)McKenney Daniel W, Pedlar John H (2003): Spatial models of site index based on climate and soil properties for two boreal tree species in Ontario, Canada. Forest Ecology and Management, 175, 497-507 https://doi.org/10.1016/S0378-1127(02)00186-XMehdinya T., Ejtehadi H., Sepehri A. (2006): Physiographic variables and the correlation between rainfall and vegetation communities present in the watershed of the Babol, Mazandaran province using geographic information systems. Journal of Agricultural Sciences and Natural Resources, 13: 99–107. (in Persian)Momeni Moghaddam T., Sagheb Talebi K.H., Akbarinia M., Akhavan M., Hosseini S.M. (2012): Impact of physiographic and edaphic factors on some of qualitative and quantitative characteristics of Juniperus trees. Case study: Layn region – Khorasan. Iranian Journal of Forest, 4: 143–156. (in Persian)Moore I.D., Gessler P.E., Nielsen G.A., Petersen G.A. (1993): Terrain attributes: Estimation methods and scale effects. In: Jakeman A.J., Beck M.B., McAleer M. (eds): Modelling Change in Environmental Systems. London, John Wiley & Sons: 189–214.O’Sullivan S., Keady E., Keane S., Irwin O’Halloran J. (2010): Data mining for biodiversity prediction in forests. In: Coelho H., Studer R., Wooldridge M. (eds): Proceedings of the 19th European Conference on Artificial Intelligence, Lisbon, Aug 16–20, 2010: 289–294.Parmentier Ingrid, Harrigan Ryan J., Buermann Wolfgang, Mitchard Edward T. A., Saatchi Sassan, Malhi Yadvinder, Bongers Frans, Hawthorne William D., Leal Miguel E., Lewis Simon L., Nusbaumer Louis, Sheil Douglas, Sosef Marc S. M., Affum-Baffoe Kofi, Bakayoko Adama, Chuyong George B., Chatelain Cyrille, Comiskey James A., Dauby Gilles, Doucet Jean-Louis, Fauset Sophie, Gautier Laurent, Gillet Jean-François, Kenfack David, Kouamé François N., Kouassi Edouard K., Kouka Lazare A., Parren Marc P. E., Peh Kelvin S.-H., Reitsma Jan M., Senterre Bruno, Sonké Bonaventure, Sunderland Terry C. H., Swaine Mike D., Tchouto Mbatchou G. P., Thomas Duncan, Van Valkenburg Johan L. C. H., Hardy Olivier J. (2011): Predicting alpha diversity of African rain forests: models based on climate and satellite-derived data do not perform better than a purely spatial model. Journal of Biogeography, 38, 1164-1176 https://doi.org/10.1111/j.1365-2699.2010.02467.xPfeffer Karin, Pebesma Edzer J., Burrough Peter A. (2003): Mapping alpine vegetation using vegetation observations and topographic attributes. Landscape Ecology, 18, 759-776 https://doi.org/10.1023/B:LAND.0000014471.78787.d0Pourbabaee H. (1998): Biodiversity of wooden plants in the forests of Gillan. [Ph.D. Thesis.] Tehran, Tarbiat Modares University: 264. (in Persian)Qomioghli A.S., Hosseini M., Mataji A., Jalali G.H. (2006): Biodiversity of wooden plants on different soil in two different plant communities. Journal of Biology, 20: 200–207. (in Persian)Saatchi Sassan, Buermann Wolfgang, ter Steege Hans, Mori Scott, Smith Thomas B. (2008): Modeling distribution of Amazonian tree species and diversity using remote sensing measurements. Remote Sensing of Environment, 112, 2000-2017 https://doi.org/10.1016/j.rse.2008.01.008Shannon C.E., Weaver W. (1949): The Mathematical Theory of Communication. Urbana, University of Illinois Press: 163.Shataee Shaban, Kalbi Syavash, Fallah Asghar, Pelz Dieter (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 https://doi.org/10.1080/01431161.2012.682661Shirzad M.A., Tabari M. (2011): Effect of some environmental factors on diversity of woody plants in Junipeus excelsa habitat of Hezarmasjed mountains. Iranian Journal of Biology, 24: 800–808. (in Persian)SIMPSON E. H. (1949): Measurement of Diversity. Nature, 163, 688-688 https://doi.org/10.1038/163688a0Smith Benjamin, Wilson J. Bastow (1996): A Consumer's Guide to Evenness Indices. Oikos, 76, 70- https://doi.org/10.2307/3545749Stephenson C.M., MacKenzie M.L., Edwards C., Travis J.M.J. (2006): Modeling establishment probabilities of an exotic plant, Rhododendron ponticum, invading a heterogeneous woodland landscape using logistic regression with spatial autocorrelation Ecological Modeling, 193: 747–758.van der Maarel E. (2005): Vegetation Ecology. London, Blackwell Publishing: 273.Whittaker R.H. (1977): Evolution of species diversity in land communities. Evolutionary Biology, 10: 1–67.Wilson J.P., Gallant J.C. (2000): Terrain Analysis: Principles and Applications. New York, John Wiley & Sons: 520.Yazdani S. (2011): Quantitative estimation of forest characteristics using QuickBird images. [MSc Thesis.] Gorgan, Gorgan University of Agricultural Sciences and Natural Resources: 129. (in Persian)Zimmermann Niklaus E., Kienast Felix (1999): Predictive mapping of alpine grasslands in Switzerland: Species versus community approach. Journal of Vegetation Science, 10, 469-482 https://doi.org/10.2307/3237182