Authors: Kostantinos Demertzis Lazaros Iliadis Stavros Avramidis Yousry A ElKassaby
Publish Date: 2015/11/16
Volume: 28, Issue: 3, Pages: 505-519
Abstract
Several machine learning models were used to predict interior spruce wood density using data from openpollinated progeny testing trial The data set consists of growth height and diameter which were used to estimate individual tree volume and wood quality wood density determined by Xray densitometry resistance to drilling and acoustic velocity attributes for a total of 1146 trees growing on comparable sites in interior British Columbia Various machine learning models were developed for estimating wood density The multilayer feedforward artificial neural networks and gene expression programming provided the highest predictability as compared to the other methods tested including those based on classical multiple regression which was considered as the comparisons benchmark The utilization of machine learning models as a credible method for estimating wood density using available growth data as an indirect method for determining trees wood density is expected to become increasingly helpful to forest managers and tree breedersThanks to Irena Fundova and Tomas Funda for data collection and Barry Jaquish for access to progeny test sites Funds from the Natural Sciences and Engineering Research Council of Canada’s Discovery and IRC grants FPInnovations and the Johnson’s Family Forest Biotechnology Endowment to YAE are highly appreciated
Keywords: