Artificial intelligence with deep learning algorithms to model relationships between total tree height and diameter at breast height

Abstract

Aim of Study: As an innovative prediction technique, Artificial Intelligence technique based on a Deep Learning Algorithm (DLA) with various numbers of neurons and hidden layer alternatives were trained and evaluated to predict the relationships between total tree height (TTH) and diameter at breast height (DBH) with nonlinear least squared (NLS) regression models and nonlinear mixed effect (NLME) regression models.Area of Study: The data of this study were measured from even-aged, pure Turkish Pine (Pinus brutia Ten.) stands in the Kestel Forests located in the Bursa region of northwestern Turkey.Material and Methods: 1132 pairs of TTH-DBH measurements from 132 sample plots were used for modeling relationships between TTH, DBH, and stand attributes such as dominant height (Ho) and diameter (Do).Main Results: The combination of 100 # neurons and 8 # hidden layer in DLA resulted in the best predictive total height prediction values with Average Absolute Error (0.4188), max. Average Absolute Error (3.7598), Root Mean Squared Error (0.6942), Root Mean Squared error % (5.2164), Akaike Information Criteria (-345.4465), Bayesian Information Criterion (-330.836), the average Bias (0.0288) and the average Bias % (0.2166), and fitting abilities with r (0.9842) and Fit Index (0.9684). Also, the results of equivalence tests showed that the DLA technique successfully predicted the TTH in the validation dataset.Research highlights: These superior fitting scores coupled with the validation results in TTH predictions suggested that deep learning network models should be considered an alternative to the traditional nonlinear regression techniques and should be given importance as an innovative prediction technique.Keywords: Prediction; artificial intelligence; deep learning algorithms; number of neurons; hidden layer alternatives.Abbreviations: TTH (total tree height), DBH (diameter at breast height), OLS (ordinary least squares), NLME (nonlinear mixed effect), AIT (Artificial Intelligence Techniques), ANN (Artificial Neural Network), DLA (Deep Learning Algorithm), GPU (Graphical Processing Units), NLS (nonlinear least squared), RMSE (root mean squared error), AIC (Akaike information criteria), BIC (Bayesian information criterion), FI (fit index), AAE (average absolute error), BLUP (best linear unbiased predictor), TOST (two one-sided test method).