Harvesting wind damaged trees: a study of prediction of windthrow damage in mixed-broadleaf stands via a machine learning model

Abstract

ABSTRACT Due to climate change, windstorms are becoming increasingly common resulting in the destruction not only of extensive forest areas but, quite often, of small-sized and scattered forest lands, thereby adversely affecting both the productivity and the safety of workers employed in the harvest of windblown trees. In the present study, an attempt is made to identify and record areas in the northeastern forests of Greece covered by mixed stands of conifers and broadleaves that experienced massive windthrow following local storms. Our results reveal that where Pinus sylvestris was mixed either with Quercus sp. or with Fagus sylvatica, it had been substantially protected, while in plots where it stood on its own it had been extensively uprooted. On the other hand, Picea abies, even if it was mixed with Fagus sylvatica and Pinus sylvestris, had been blown down to a large extent. Based on tree-level data, local topographic features, forest characteristics, and the mechanical properties of green wood, a reliable model, to be used for the prediction of similar disturbances in the future, has been selected after a thorough comparative study of the most well-known intelligent Machine Learning (ML) algorithms. Specifically, Random Forest Classifier, k-Neighbors Classifier, Decision Tree Classifier, Light Gradient Boosting Machine, Gradient Boosting Classifier, Ada Boost Classifier, Ridge Classifier, Linear Discriminant Analysis, Logistic Regression, Naive Bayes, SVM – Linear Kernel, and Quadratic Discriminant Analysis were evaluated and compared using six performance measures (confusion matrix, accuracy, precision, recall, F1-score, and ROC).