Abstract
In managed forests, windstorm disturbances reduce the yield of timber by imposing the costs of unscheduled clear-cutting or thinning operations. Hyrcanian forests are affected by permanent winds, with more than 100 km/h which cause damage forest trees and in result of the tree harvesting and gap creation in forest stands, many trees failure accidents happen annually. Using machine learning approaches, we aimed to compare the multi-layer perceptron (MLP) neural network, radial basis function neural network (RBFNN) and support vector machine (SVM) models for identifying susceptible trees in windstorm disturbances. Therefore, we recorded 15 variables in 600 sample plots which are divided into two categories: 1. Stand variables and 2.Tree variables. We developed the tree failure model (TFM) by artificial intelligence techniques such as MLP, RBFNN, and SVM. The MLP model represents the highest accuracy of target trees classification in training (100%), test (93.3%) and all data sets (97.7%). The values of the mean of trees height, tree crown diameter, target tree height are prioritized respectively as the most significant inputs which influence tree susceptibility in windstorm disturbances. The results of MLP modeling defined TFMmlp as a comparative impact assessment model in susceptible tree identification in Hyrcanian forests where the tree failure is in result of the susceptibility of remained trees after wood harvesting. The TFMmlp is applicable in Hyrcanian forest management planning for wood harvesting to decrease the rate of tree failure after wood harvesting and a tree cutting plan could be modified based on designed environmental decision support system tool to reduce the risk of trees failure in wind circulations.
Highlights
Windstorm disturbances occur when sudden changes happen in wind loading and trees have not acclimatized to new conditions of the site[1] in thinned or adjacent to clear-cut stands
Forest managers need forest inventory data and maybe the main TFMmlp application would be in protected forest or where the forests are facing windstorms more frequently. Such as other prediction models in forests43–46,50,51, TFMmlp was developed for forest managers to assess quickly the impact of cutting trees or thinning stands on tree failure risk in forest
T FMmlp requires extensive data sets of actual wind-damage for its development and could be applied to other forests if the new region conditions are comprehensively covered within T FMmlp training data set
Summary
Windstorm disturbances occur when sudden changes happen in wind loading and trees have not acclimatized to new conditions of the site[1] in thinned or adjacent to clear-cut stands. We believe that it is possible to develop mathematical models to predict the role of wind in trees stability by discovering the response of trees to sudden windstorms. ANNs use multiple training algorithms and rules and less formal statistical training These methods have very distinctive potential to determine all possible interactions between tree failure and ecological variables[11]. The main objectives were to: (1) model tree failure potential in the windstorm of forest lands; (2) compare different machine learning techniques to identify the most accurate model; (3) prioritize the model inputs (tree and stand variables) using sensitivity analysis of the model; and (4) designing environmental decision support tool for wind-susceptible tree identification
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
