Plane tree risk assessment in urban space using Artificail Neural Network

Document Type : Original Article


1 Department of Forest Science, Faculty of Natural Resources and Earth Sciences, Shahrekord University, Shahrekord, Iran

2 Deptartment of Rangeland and Watershed management, Faculty of Natural Resources and Earth Sciences, University of Shahrekord, Shahrekord, Iran


As one of the most valuable parts of a municipal system, the green space has long been praised. For that matter, all the data related to street-side trees must be assessed and recorded. A large part of old plane trees (Platanus orientalis) planted in industrial, dense populated cities are subjected to all kinds of air and water pollutions, frequent droughts and various physical stresses, which make them less likely to sustain. Identification of the most vulnerable tree individuals can be prioritized by a variety of statistical methods. A less applied statistical model in this field is the Artificial Neural Network (ANN). In this study, we present the results of applying ANN model in risk assessment of plane trees planted along Kuala Lumpur Avenue in Isfahan in 2018.
Material and methods:
In the current study, the risk level of keeping plane trees in Kuala Lumpur Ave. Isfahan was studied using data acquired by a full survey method, and using quantitative tree body proportions and few risk factors (qualitative or imperfect properties). Following coining the share of each of seven hazard criteria and their trio importance indices, a Kruskal-Wallis test compared the number of trees in different risk levels. Then, all the trees were scored via the biased levels of their risk level. Accordingly, based on the weighted scores, they were divided into five hazardous categories. To develop an understanding of the quantitative variables, risk factors, weight parameters, and hazard classes, we carried out a principle component analysis (PCA) and a multi-layer perceptron (MLP) network procedure.
Results and discussion:
The results of the proportion of each hazard index revealed the importance of the trunk and root wounds (83%), the structural tree weakness (61%), root problems (54%), and branch and twig dieback (50%). Also, results of Kruskal-Wallis test showed that the risk levels of the planted trees can be significantly classified into four classes of: with no risk or healthy, low, moderate, and high-risk classes, at one percent error level. The results of Duncan's mean test showed that the number of trees in no risk and low-risk classes were significantly higher than the other classes at one percent error level. The results of the PCA indicated that the first and second components explained 44.69 percent of the total variation. The risk and weighting parameters of the branch and twig dieback, the tree diameter, advanced decay, and wound on the trunk and root were highly and positively correlated. In general, the two variables of the trunk and root wounding, as well as branch and twig dieback, were among the most important variables in terms of risk assessment of the plane trees. The high coefficient of determination values of training, validation, verification, and finally, all neural network data (0.999, 0.949, 0.996, and 0.991) and the least mean square error values (training data = 0.052, verification 0.114, and validation = 0.044) indicated the accuracy and desirability of the ANN in the prediction of the risk classes for street side trees.
According to the results of risk assessment diagnostic criteria and main components analysis, the two variables of trunk wound and root and branch mortality of plane trees should be regularly reviewed. Moreover, decision-makers may use the neural network method to identify and detect the risk possibility of planted trees. Therefore, this approach can be proposed as a suitable and useful solution in urban green space management and preventive measures.


  1. Alamdari, A.A., Dosti Aref, A., Karimi Mahabadi, R. and Rajabi, Z., 2011. Special topics in electrical and computer engineering with Matlab. Negarande Danesh Press. Tehran.
  2. Albers, J. and Hayes, E., 1993. How to detect, assess and correct hazard trees in recreational areas. Department of Natural Resources Press, Minnesota DNR, USA.
  3. Azizi, H.R. and Montazeri, M., 2015. Anticipated monthly temperatures for selected stations in Isfahan province using artificial neural network multi-layer Perceptron. Geographical Researches Quarterly Journal. 30(3), 241-258.
  4. Banj Shafiei, A., Samadzadeh Gargari, Kh., Seyedi, N. and Alijanpour, A., 2016. Study of qualitative, quantitative and risk possibility of Plane trees of Urmia. Forest Research and Development. 1(4), 319-335.
  5. Barazmand, S., Shataei, Sh., Kavosi, M.R. and Habashi, H., 2011. Spatial distribution of tree crown dieback and its relation with some environmental factors and road network. Journal of Wood & Forest Science and Technology. 19(3), 159-174.
  6. Dunster, J.A. 1996. Hazard tree assessments: Developing a species profile for western hemlock. Journal of Arboriculture. 22(1), 51- 57.
  7. Fazio, J.R., 1989. How to recognize and prevent hazard trees. Tree City USA Bulletin, Nebraska City. NE: National Arbor Day Foundation. USA.
  8. Ghehsareh Ardestani, E., Bassiri, M., Tarkesh, M. and Borhani, M., 2010. Distributions of species diversity abundance models and relationship between ecological factors with Hill(N1) species diversity index in 4 range sites of Isfahan Province. Journal of Range and Watershed Management, Iranian Journal of Natural Resources. 63(3), 387-397.
  9. Hassanzad Navroodi, I., Namiranian, M. and Zahedi Amiri, Gh., 2004. An evaluation of relationship between quantitative and qualitative characteristics and site factors in the natural beech (Fagus orientalis) stands in Asalem. Iranian Journal of Natural Research. 57(2), 235-248.
  10. Harris, R.W., Clark, J.R. and Matheny, N.P., 1999. Arboriculture: Integrated management of trees, shrubs and vines, 3rded., Upper Saddle River, Prentice Hall, New Jersey.
  11. Heikkonen, J. and Varjo, J. 2004. Forest change detection applying Landsat thematic mapper difference features: A comparison of different classifiers in boreal forest conditions. Forest Science. 50(5), 579-588.
  12. Hickman, G.W., Caprile, J. and Perry, E., 1989. Oak tree hazard evaluation. Journal of Arboriculture. 15(8), 177-184.
  13. Hosseinzadeh, J. Najafifar, A. and Tahmasebi, M., 2015. Investigation on principal factors determining stand structure in Oak forests of Zagross. Journal of Plant Researches (Iranian Journal of Biology). 29(4), 766-774.
  14. Jahani, A., 2017a. Aesthetic quality evaluation modeling of forest landscape using artificial neural network. Journal of Wood and Forest Science and Technology. 24(3), 17-33.
  15. Jahani, A., 2017b. Sycamore Failure Hazard Risk modeling in urban green space. Jsaeh. 3(4), 35-48.
  16. Jahani, A. and Mohammadi Fazel, A., 2015. Aesthetic quality modeling of landscape in urban green space using artificial neural network. Journal of Natural Environment (Iranian Journal of Natural Resources). 69(4), 951-963.
  17. Kazemi Najafi, S., 2016. Nondestructive evaluation of standing trees. First Printing, Tarbiat Modarres University Publication Center, Tarbiat Modares University Press. Tehran.
  18. Kent, M. and Coker, P., 2001. Vegetation description and analysis: a practical approach. Mesdaghi, M. Publications University of Mashhad, Mashhad.
  19. Khoshgoftarmanesh, A.H., Eshghizadeh, H.R., Sanaei Ostovar, A. and Taban, M., 2013. Assessment of iron (Fe) chlorosis in Plane trees (Plantanus orintalis L.) grown in green space of Isfahan city, I: Leaf Mineral Concentration. Journal of Water and Soil Science (Journal of Science and Technology of Agriculture and Natural Resources). 20(76), 19-31.
  20. Mesdaghi, M., 2005. Plant Ecology. Publications University of Mashhad, Mashhad.
  21. Matheny, N. and Clark, J., 2009. Tree risk assessment: what we know (and what we Don’t know). Arborist New. 18(1), 28-33.
  22. Mattheck, C. and Breloer, H., 1994. Field guide for visual tree assessment (VTA). Arboricultural Journal: The International Journal of Urban Forestry. 18(1), 1-23.
  23. Mortimer, M.J. and Kane, B., 2004. Hazard tree liability in the United States: uncertain risks for owners and professionals. Urban Forestry and Urban Greening. 2(3), 159- 165.
  24. Parsamahr, A.H. and Khosravani, Z., 2017. Determining drought severity using multi- criteria decision- making based on TOPSIS method (Case study: selective stations of Isfahan Province). Iranian Journal of Range and Desert Reserch. 24(1), 16-29.
  25. Pourhashemi, M., Khosro pour, A. and Heidari, M., 2012. The assessment of hazardous oriental plane (Platanus orientalis Linn.) trees in Valiasr street of Tehran. Iranian Journal of Forest. 4(3), 265-275.
  26. Pourmajidian, M. R., Aghajani, H., Fallah, A. and Heydari, M., 2015. An investigation of dangers rate of Pine (Pinus eldarica Medw) trees in urban margins in Babol city. Natural Ecosystems of Iran. 5(4), 63-76.
  27. Raiesi, M. and Bahmani, M., 2018. Urban tree risk management (case study: Plane trees in Isfahan streets): In Proceedings International Conference on Natural Resources Management in Developing Countries. 25th Feb 2018, Department of Natural resources, Tehran University. p.8.
  28. Ravi Raja, A., 2016. Principal component analysis based assessment of trees outside forests in satellite images. Indian Journal of Science and Technology. 9(S1), 1-6.
  29. Robbins, R., 1986. How to recognize and reduce tree hazards in recreation sites. NA- FR- 31. Radnor, PA: USDA Forest Service, Northeastern Area. USA.
  30. Shahgholi, Gh., Ghafouri Chiyaneh, H. and Mesri Gundoshmian, T., 2017. Modeling of soil compaction beneath the tire using multilayer perceptron neural networks. Journal of Agricultural Machinery. 8(1), 105-118.
  31. Tahmasebi, P., 2011. Ordination multivariate analysis of ecological data. Shahrekord University Press. Iran.
  32. Zobeiry, M., 2012. Forest inventory measurement of tree and forest. Tehran University Press. Tehran.