气候变化领域集成服务门户(CCPortal): Tree failure prediction model (TFPM): machine learning techniques comparison in failure hazard assessment of Platanus orientalis in urban forestry

CCPortal

DOI	10.1007/s11069-021-04972-7
	Tree failure prediction model (TFPM): machine learning techniques comparison in failure hazard assessment of Platanus orientalis in urban forestry
	Jahani A.; Saffariha M.
发表日期	2021
ISSN	0921030X
英文摘要	Trees are generally harmed by multitude factors consisting of ecological condition and anthropogenic pressures in the cities. This study compares the multilayer perceptron (MLP) neural network, radial basis function neural network (RBFNN) and support vector machine (SVM) models for Platanus orientalis trees failure prediction in urban forest ecosystems by a detailed field survey of P. orientalis trees issues. Therefore, we recorded 12 variables in 500 target trees which are categorized into in to two groups: (1) tree variables, and (2) tree defects and disorders. We developed the tree failure prediction model (TFPM) to predict the year of trees failure by artificial intelligence techniques. Compared to MLP and RBFNN, the SVM model represents the highest entity of R2 in training (0.99), test (0.986) and all (0.989) data sets. In sensitivity analysis, the classes of tree hazard are sensitive to three variables which are: soil depth, cracks and cavities, and wind protected, respectively. The results of SVM modeling, with 97.5% classification accuracy, in comparison with MLP (94%) and RBFNN (87.9%), in test samples, introduced TFPMSVM as an ecological failure hazard assessment model for P. orientalis. Such as other prediction model in urban trees management, TFPMSVM was developed for urban forest and green spaces managers to assess the hazard of old P. orientalis trees failure for precaution actions planning timely. TFPMSVM as an environmental decision support system is applicable where the old and hazardous trees could be rehabilitated or removed before any unexpected failure occurs. © 2021, The Author(s), under exclusive licence to Springer Nature B.V.
关键词	Failure hazard Machine learning techniques Platanus orientalis Urban trees
语种	英语
来源期刊	Natural Hazards
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/206298
作者单位	Assessment and Environment Risks Department, Research Center of Environment and Sustainable Development and College of Environment, Tehran, Iran; Department of Reclamation of Arid and Mountainous Regions, College of Natural Resources, University of Tehran, Tehran, Iran
推荐引用方式 GB/T 7714	Jahani A.,Saffariha M.. Tree failure prediction model (TFPM): machine learning techniques comparison in failure hazard assessment of Platanus orientalis in urban forestry[J],2021.
APA	Jahani A.,&Saffariha M..(2021).Tree failure prediction model (TFPM): machine learning techniques comparison in failure hazard assessment of Platanus orientalis in urban forestry.Natural Hazards.
MLA	Jahani A.,et al."Tree failure prediction model (TFPM): machine learning techniques comparison in failure hazard assessment of Platanus orientalis in urban forestry".Natural Hazards (2021).