Predicting fir trees stem diameters using Artificial Neural Network models

The financial exploitation of forests constitutes an important part of human activity. This effort is being made in order to conserve the sustainable exploitation while avoiding the degradation of the environment. One of the most important operations in forest mensuration is the estimation of the volume of sample trees. Such estimation may be used in order to conduct a large stand inventory, construct volume tables, develop tree competition and growth models, predict tree mortality from diameter growth, and implement a number of other activities. Efficiency, the trade-off between cost and precision, is of paramount importance in the estimation of volume. The aim of this paper is to examine the applicability of Artificial Neural Network models (ANNs), in the prediction of fir trees stem over bark diameters at 5.3, 9.3, 13.3, 17.3, 21.3, 25.3, 29.3 and 33.3 meters above ground. The values of these diameters are necessary for an efficient estimation of a single tree volume using the well-known Smalian's sectional method. The system proposed in this paper can be applied in forest inventory making an accurate estimate of the volume of a sample tree based on only two diameter measurements (stump diameter, d0.3 and diameter at breast height, d1.3 ) and an estimate of the total tree height (h). Training of the ANNs was achieved through the cascade correlation algorithm, which is a feed-forward and supervised algorithm. Kalman's learning rule was used to modify the artificial neural networks weights. These networks are designed by putting weights between neurons, through the use of the hyperbolic-tangent function of training. The estimation system proposed is capable of replacing many standard forestry mensuration procedures due to its efficiency and accuracy. The neural network models were found to be appropriate and accurate for the prediction of all diameters.

[1]  Harold E. Burkhart,et al.  Evaluation of Two Methods for Cubic-Volume Prediction of Loblolly Pine to Any Merchantable Limit , 1980 .

[2]  G. Gertner,et al.  Modeling red pine tree survival with an artificial neural network , 1991 .

[3]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[4]  R. Bailey.  A compatible volume-taper model based on the Schumacher and Hall generalized constant form factor volume equation. , 1994 .

[5]  Denis J. Dean,et al.  Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables , 1999 .

[6]  Howard B. Demuth,et al.  Neutral network toolbox for use with Matlab , 1995 .

[7]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[8]  V. Clark Baldwin,et al.  Predicting Diameter Distributions of Longleaf Pine Plantations: A Comparison Between Artificial Neural Networks and Other Accepted Methodologies , 2001 .

[9]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[10]  Maria J. Diamantopoulou,et al.  Artificial neural networks as an alternative tool in pine bark volume estimation , 2005 .

[11]  L. Zhang,et al.  Comparison of Neural Networks and Statistical Methods in Classification of Ecological Habitats Using FIA Data , 2003 .

[12]  Dieter Merkl,et al.  Estimating tree mortality of Norway spruce stands with neural networks , 2001 .

[13]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[14]  F. L. Xiong,et al.  A method for estimating the number of hidden neurons in feed-forward neural networks based on information entropy , 2003 .

[15]  M. Philip,et al.  Measuring Trees and Forests , 1994 .

[16]  Richard A. Brown,et al.  Introduction to random signals and applied kalman filtering (3rd ed , 2012 .

[17]  Leah L. Rogers,et al.  Solving Problems in Environmental Engineering and Geosciences with Artificial Neural Networks , 1996 .

[18]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[19]  Ali Zilouchian,et al.  FUNDAMENTALS OF NEURAL NETWORKS , 2001 .

[20]  Simon A. Corne,et al.  Predicting forest attributes In southeast Alaska using artificial neural networks , 2004 .

[21]  A. Martin,et al.  Taper and volume equations for selected Appalachian hardwood species , 1981 .