Comparison of Random Forest Models, Support Vector Machine and Multivariate Linear Regression for Biodiversity Assessment in the Hyrcanian Forests

Document Type : Research Paper


1 Department of forest, Research Institute of Forests and Rangelands, Agricultural Research, Education and Extension Organization (AREEO), Tehran, Iran

2 Department of Environment, Faculty of Natural Resources, University of Tehran

3 Department of Forestry, Faculty of Natural Resources, Sari Agriculture Sciences and Natural Resource University, Sari


Biodiversity is an important structural feature of dynamic and complex forest ecosystems. One of the most challenging and important issues in assessing the structure of forest ecosystems is understanding the relationship between biodiversity and environmental factors. Hyrcanian Forests are considered a biodiversity hotspot in the world and have special and unique features that have led to an emphasis and importance of biodiversity conservation in these forests. The aim of this study was to investigate the effect of biotic and abiotic factors on the diversity and richness of tree species in Hyrcanian Forests from the west of Gilan province to the east of Golestan province. For this purpose, using 655 fixed sample plots (0.1 hectare), the diversity of trees in 3 provinces in the northern Iran from east to west of the Caspian Sea was analyzed. A combination of non-parametric models including random forest (RF) and support vector machine (SVM) and linear regression models were used to investigate the relationship between tree diversity and biotic and abiotic factors. Biotic and abiotic variables included the number of trees per hectare, diameter, respectively. Basal area (BA), Basal Area in Largest tree (BAL), slope, aspect and elevation. Evaluation statistics including the coefficient of determination, RMSE and percentage RMSE error showed that the random forest model was the best model to determine the relationship between biodiversity and environmental factors and has suitable accuracy for determining biodiversity changes in the northern forests of Iran.


  1. Abedi, T., Hoseini, S.A., & Naghdi, R. (2020). Study of relationship between soil mechanical characteristic and landslide in forest road route (Case Study: Chafroud Watershed Guilan Prov.). Journal of Watershed Management, 1, 17-29 (In Persian).
  2. Bayat, M., Pukkala, T., Namiranian, M., & Zobeiri, M. (2013). Productivity and optimal management of the uneven-aged hardwood forests of Hyrcania. European Journal of Forest Research, 132(5-6), 851–864.
  3. Bayat, M., Noi, P.T., Zare, R., & Bui, D.T. (2019). A semi-empirical approach based on genetic programming for the study of biophysical controls on diameter-growth of Fagus orientalis in northern Iran. Remote Sensing11(14), 1-19.
  4. Bayat, M., Bettinger, P., Heidari, S., Henareh Khalyani, A., Jourgholami, M., & Hamidi, S.K. (2020). Estimation of tree heights in an uneven-aged, mixed forest in northern Iran using artificial intelligence and empirical models. Forests11(3), 1-18.
  5. Bayat, M., Bettinger, P., Heidari, S., Hassani,M, 2021a, Ten-year estimation of Fagus orientalis Lipsky increment in natural forests: A Comparison of artificial neural networks model, multiple linear regression and actual increment. 2021 Forestry: An International Journal of Forest Research 94(4), pp. 598-609
  6. Bayat, M., Burkhart, H., Namiranian, M., Hamidi, S.K., Heidari, S. and Hassani, M., 2021b. Assessing Biotic and Abiotic Effects on Biodiversity Index Using Machine Learning. Forests 2021, 12, 461.
  7. Bourque, C.P.A., & Bayat, M. (2015). Landscape variation in tree species richness in northern Iran forests. PLoS ONE, 10(4), 1-17.
  8. Bourque, C.P.A., Bayat, M., & Zhang, C. (2019). An assessment of height–diameter growth variation in an unmanaged Fagus orientalis‑dominated forest. European Journal of Forest Research, 138(4), 607–621.
  9. Burkhart, H.E., & Tomé, M. (2012). Modeling forest trees and stands. Springer Science & Business Media, 9, 1-18.
  10. Chen, J., Yang, H., Man, R., Wang, W., Sharma, M., Peng, C., Parton, J., Zhu, H. & Deng, Z., (2020). Using machine learning to synthesize spatiotemporal data for modelling DBH-height and DBH-height-age relationships in boreal forests. Forest Ecology and Management466, 1-15.
  11. Chu C., Lutz J.A., Král K., Vrška T., Yin X., Myers J.A., et al.. (2019). Direct and indirect effects ofclimate on richness drive the latitudinal diversity gradient in forest trees.Ecology Letter, 22 (2), 245 - 255.
  12. Cui, W., & Zheng, X.-X. (2016). Spatial heterogeneity in tree diversity and forest structure of evergreen broadleaf forests in southern China along an altitudinal gradient. Forests, 7, 216.
  13. Eshaghi, M., & Shataee joybari, S. (2016). Preparation map of Forest Fire Risk Using SVM, RF & MLP Algorithms (Case Study: Golestan National Park, Northeastern Iran), Journal of Wood and Forest Science and Technology, 23(4), 1333-154. )In Persian).
  14. Jafarian, Z., & Kargar, M. (2017). Comparison of Random Forest (RF) and Boosting Regression Tree (BRT) For Prediction of Dominant Plant Species Presence in Polour Rangelands, Mazandaran Province. J. Appl. Ecol, 6 (1), 41-55 (In Persin).
  15. Júnior, I.D.S.T., Torres, C.M.M.E., Leite, H.G., de Castro, N.L.M., Soares, C.P.B., Castro, R.V.O. & Farias, A.A. (2020). Machine learning: Modeling increment in diameter of individual trees on Atlantic forest fragments. Ecological Indicators117, 25-35
  16. Hamidi, S.K., de Luis, M., Bourque, C.PA. Bayat, M et al. Projected biodiversity in the Hyrcanian Mountain Forest of Iran: an investigation based on two climate scenarios. Biodivers Conserv (2022).
  17. Kebede, M., Yirdaw, E., Luukkanen, O., & Lemenih, M. (2013). Plant community analysis and effect of environmental factors on the diversity of woody species in the moist Afromontane forest of Wondo Genet, South Central Ethiopia. Biodiversity.Res Conser, 29,
  18. Lee Sunmin Kim, J. C., Jung, H. S., Lee, M. J., & Lee, S. (2017). Spatial prediction of flood susceptibility using random-forest and boosted-tree models in Seoul metropolitan city, Korea. Geomat. Nat. Risk, 8, 1185–1203.
  19. Liu, Z., Peng, C., Work, T., Candau, J.N., DesRochers, A., & Kneeshaw, D. (2018). Application of machine-learning methods in forest ecology: recent progress and future challenges. Environmental Reviews26(4), 339-350.
  20. Monarrez-Gonzalez, J.C., Gonzalez-Elizondo, M.S., Marquez-Linares, M.A., Gutierrez-Yurrita, P.J. & Perez-Verdin, G., (2020). Effect of forest management on tree diversity in temperate ecosystem forests in northern Mexico. Plos one15(5), 38-50.
  21. Mountrakis, G., Im, J., & Ogole, C. (2011), Support Vector Machines in Remote Sensing:   A Review, ISPRS. Journal of Photogrammetry and   Remote Sensing, 66, 247-259.
  22. Oyebade, B.A., Eguakun, F.S., & Duru, B.N. (2020). Tree basal area models and density for selected plantation species in swamp forest zone of Rivers State, Nigeria. World News of Natural Sciences30(3), 281-296.
  23. Roslin T., Hardwick B., Novotny V., Petry W.K., Andrew N.R., et al.. (2017). Higher predation risk for insect prey at low latitudes and elevations. Science, 356(6339), 742 -744.
  24. Sharma, M., & Parton, J. (2007). Height–diameter equations for boreal tree species in Ontario using a mixed-effects modeling approach. Forest Ecology and Management,249(3),187-198.
  25. Shen, W., Wang, J., Ali, A. & Li, M. (2020). Machine learning and geostatistical approaches for estimating aboveground biomass in Chinese subtropical forests.
  26. Šímová, I., Storch, D., Keil, P., Boyle, B., Phillips, O.L., & Enquist, B.J. (2011). Global species–energy 652 relationship in forest plots: role of abundance, temperature and species climatic 653 tolerances. Ecol. Biogeogr, 20, 842–856.
  27. Tiwari, O.P., Sharma, C.M., & Rana, Y.S. (2020). Influence of elevation and slope-aspect on diversity, regeneration and structure of some moist temperate forests of Garhwal Himalaya. Tropical Ecology, 61(2).278-289.
  28. Vafaei, S., Soosani, J., Adeli, K., Fadaei, H., Naghavi, H., Pham, T., & Bui, D. (2018). Improving Accuracy Estimation of Forest Aboveground Biomass Based on Incorporation of ALOS-2 PALSAR-2 and Sentinel-2A Imagery and Machine Learning: A Case Study of the Hyrcanian Forest Area (Iran). Remote Sens, 10 (172), 1-21.
  29. Westreich, D., Lessler, J., Funk, M.J. (2010). Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression. Clin. Epidemiol, 63, 826–833. jclinepi.2009.11.020.
  30. Woldu, G., Solomon, N., Hishe, H., Gebrewahid, H., Gebremedhin, M.A., & Birhane, E. (2020). Topographic variables to determine the diversity of woody species in the exclosure of Northern Ethiopia. Heliyon6 (1), p.e03121.
  31. Wood, S. (2008). Fast stable direct fitting and smoothness selection for generalized additive models. Journal of Royal Statistical Society,
  32. Yadegarnejad, S.A., Sagheb-Talebi, Kh., Heidari, H., Moayeri, M.H., & Mortazavi. S.M. (2017). Evaluation of application of the 15d method in Loveh Forest, Golestan Province. Iranian Journal of Forest and Poplar Research, 25 (1): 160-171 (In Persian).
  33. Yao, L., Ding, Y., Xu, H., Deng, F., Yao, L., Ai, X., & Zang, R. (2020). Patterns of diversity change for forest vegetation across different climatic regions-A compound habitat gradient analysis approach. Global Ecology and Conservation, p.e01106.
  34. Zarandian, A., Baral, H., Yavari, A.R., Jafari, H.R., Stork, N.E., Ling, M.A., & Amirnejad, H. (2016). Anthropogenic decline of ecosystem services threatens the integrity of the unique Hyrcanian (Caspian) forests in Northern Iran. Forests7 (3), p.51.
  35. Zhang J., Li M., & Nie E. (2014). Pattern of functional diversity along an altitudinal gradient in the Baihua Mountain Reserve of Beijing, China. Brazilian Journal of Botany, 1, 37-45.