Tree failure prediction model (TFPM): machine learning techniques comparison in failure hazard assessment of Platanus orientalis in urban forestry

Ali Jahani () and Maryam Saffariha ()
Additional contact information
Ali Jahani: Research Center of Environment and Sustainable Development and College of Environment
Maryam Saffariha: University of Tehran

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, 2022, vol. 110, issue 2, No 3, 898 pages

Abstract: Abstract 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.

Keywords: Platanus orientalis; Machine learning techniques; Urban trees; Failure hazard (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11069-021-04972-7 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:nathaz:v:110:y:2022:i:2:d:10.1007_s11069-021-04972-7

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11069

DOI: 10.1007/s11069-021-04972-7

Access Statistics for this article

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards is currently edited by Thomas Glade, Tad S. Murty and Vladimír Schenk

More articles in Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards from Springer, International Society for the Prevention and Mitigation of Natural Hazards
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().