Presenting a Numerical Model for Estimating the Trunk Weight of Popolus tree (Popolus Deltoids), Based on Multiple Linear Regression.
sina pourrajabali 1 , Vahid Hemati 2 * , Alireza eslami 3 , seyed armin hashemi 4 , سید یوسف ترابیان 5
1 - Department of Forestry, Islamic Azad University, Lahijan branch, Lahijan, IRAN
2 - Department of Forestry, Islamic Azad University, Lahijan branch, Lahijan, IRAN
3 - Department of Horticultural Sciences, Islamic Azad University, Rasht Branch, Rasht, IRAN
4 - PhD in Forestry, Associate Professor, Department of Forestry, Lahijan Branch, Islamic Azad University, Lahijan, Iran
5 - 1) Department of Forestry, Islamic Azad University, Lahijan branch, Lahijan, IRAN
Keywords: Numerical Modeling, Multivariate Linear Regression, Popolus Deltoids, Tree Trunk Weight Estimation.,
Abstract :
Measuring the weight of trees is always possible after cutting trees and it is accompanied by many difficulties and problems. The current research is designed with the aim of providing a numerical model to estimate the weight of the tree trunk before cutting. In this regard, 400 trees were examined in the afforested areas in the west of Gilan province. Before cutting them, 11 variables were measured from each tree, which were considered as independent variables or inputs in modeling. After cutting the trees, the weight of the tree trunks was obtained by direct measurement through a scale. Pearson's correlation test showed that the variables of diameter at 1.30 meters height, diameter at 3 meters height, diameter at 4 meters height, collar diameter and trunk height are the most effective variables on tree trunk weight. Then, based on these 5 variables, the input combinations were arranged into the model and the Multiple Linear Regression model was tested and evaluated. The results showed that the presented model is able to estimate the weight of tree trunks with RMSE = 65.98 kg and R2 = 0.919 by only having two variables of 1.30 diameter and trunk height. According to the NS and NRMSE criteria, which were reported as 0.909 and 0.080, respectively, the quality of the estimations of this model is considered excellent. This achievement can provide the possibility for the managers, planners and users of the wood industry to estimate the trunk weight of each tree with an acceptable error before cutting the trees.
Aghelpour, P. and Varshavian, V. (2020) Evaluation of stochastic and artificial intelligence models in modeling and predicting of river daily flow time series. Stochastic Environmental Research and Risk Assessment, 34(1): 33-50.
Bayat, M. (2017) Predicting and assessing the tree species survival and determining physiographic factors affecting on it in Mazandaran province Forests using artificial neural networks. Journal of Natural Environment, 70(4): 771-782.
Bayati, H. and Najafi, A. (2011) Application of artificial intelligence in trees stem volume estimation, Journal of Renewable Natural Resources Research, 2(4): 52-59.
Bayati, H. and Najafi, A. (2013) Performance comparison artificial neural networks with regression analysis in tree’s trunk volume estimation. Forest and Wood Products, 66(2): 177-191.
Cleugh, H.A.‚ 2004 Effects of Windbreak on Air Flow, Micro Climate & Crop Yield. USA: Springer Link, Inc.
Ghanbari, F., Shataee, Sh., Dehghani, A.A. and Ayoubi, Sh. (2009) Tree density estimation of forests by terrain analysis and artificial neural network. Journal of Wood & Forest Science and Technology, 16(4): 25-42.
Gorzin, F., Namiranian, M., Omid, M. and Bayat, M. (2017) Prediction commercial and cordwood volume of broadleaves using Artificial Neural Networks, Case study: Gorazbon distric of Kheyrood forest, Nowshahr. Iranian Journal of Forest and Poplar Research, 25(3): 517-527.
Guillemette, T. and DesRochers, A. (2008) Early growth and nutrition of hybrid poplars fertilized at planting in the boreal forest of western Quebec. Forest Ecology and Management, 255(7): 2981-2989.
Guo, X.Y. and Zhang, X.S. (2010) Performance of 14 hybrid poplar clones grown in Beijing, China. Biomass and Bioenergy, 34(6): 906-911.
Lefroy, E. (1991) Trees and shrubs as sources of fodder in Western Australia, The role of trees in sustainable agriculture conference, Albury NSW, September, pp. 19-32.
Mosaffaei, Z. and Jahani, A. (2021) Modeling of ash (Fraxinus excelsior) bark thickness in urban forests using artificial neural network (ANN) and regression models. Modeling Earth Systems and Environment, 7(3): 1443-1452.
Nelson, N.D., Meilan, R., Berguson, W.E., McMahon, B.G., Cai, M. and Buchman, D. (2019) Growth performance of hybrid poplar clones on two agricultural sites with and without early irrigation and fertilization. Silvae Genetica, 68(1): 58-66.
Ober, Pieter Bastiaan (2013) Introduction to linear regression analysis.
Peyrov, S., Najafi, A. and Alavi, S.J. (2014) Prediction of forest roadway using artificial neural network and multiple linear regressions. Forest Sustainable Development, 1(3): 285-296.
Szekai, Z., Fengjue, L., Daoqun, Z., Qingxiao, L., Xinsheng, M. and Zhenlei, Z. (1998) Utilization of poplar leaf as fodder. Agroforestry system in China.
Taylor, K.E. (2001) Summarizing multiple aspects of model performance in a single diagram. Journal of Geophysical Research: Atmospheres, 106(D7): 7183-7192.
Welham, C., Van Rees, K., Seely, B. and Kimmins, H. (2007) Projected long-term productivity in Saskatchewan hybrid poplar plantations: Weed competition and fertilizer effects. Canadian Journal of Forest Research, 37(2): 356-370.
Woodruff, N. P., & Zingg, A. W. (1952). Wind-tunnel studies of fundamental problems related to windbreaks (Vol. 112). US Department of Agriculture, Soil Conservation Service.