Assessing regeneration in unevenaged mixed species stands

Estimating regeneration establishment is a hampered by the difficulty in collecting regeneration data and random impacts in the occurrence of regeneration. Artificial neural networks represent a computational methodology widely used to uncover the structure of a large variety of data. In general, one may recommend the application of neural networks in areas characterized by noise, poorly understood intrinsic structure and changing characteristics. Each of those characteristics is present in predicting regeneration establishment within uneven aged mixed species stands. In this project we develop a design and estimation procedure to predict regeneration establishment using data from the experimental forest, University of Agriculture in Vienna, Austria. The result of the study should provide us with tools to estimate the number of juvenile trees per unit area, the relative percentage of individuals by tree species and the mean regeneration height needed to initialize existing juvenile tree growth models.