Evaluation of potential modeling approaches for Scots pine stem diameter prediction in north-eastern Turkey

Abstract Critical forest management decisions are strongly supported by the knowledge of forest ecosystems and their features. There is a growing trend towards using models to predict the most accurate yield projections for forest management. In this research area, features of standing trees, such as diameters along the tree bole, are of much interest. This paper is focused on the construction and evaluation of potential modeling approaches for Scots pine stem diameter prediction in north-eastern Turkey, including (1) fixed-effects, (2) mixed-effects, (3) three and five quantile regression, and (4) an artificial neural network modeling techniques. Nonlinear fixed-effects, mixed-effects, and both quantile regression models were based on a variable exponent taper equation, while the Levenberg-Marquardt algorithm was investigated for the artificial neural network (LMANN) models construction. Parameters of the tested models were calibrated by the use of several stem diameter measurements obtained at relative height positions, with models’ superior performances in diameter predictions when the information of the additional diameter measured at 60% of total height, was included. Evaluation statistics show that both quantile regression and mixed-effects models improved results as compared to fixed-effects model. Overall, LMANN models achieved the best performance with higher accuracy for the Scots pine stem diameter prediction for the whole tree as well as for sections within the tree based on the ten relative height classes. Similarly to previous findings, the results of this study support that the use of mixed-effects modeling increases flexibility and efficiency of taper equations for stem diameter prediction. Moreover, the LMANN modeling approach was evaluated as superior according to its adequacy in predicting diameters along the tree stem. Therefore, the usage of the LMANNs for the tree stem diameter prediction can be a very useful tool in forest management practice and thus worth consideration.

[1]  Maria J. Diamantopoulou,et al.  Estimation of Weibull function parameters for modelling tree diameter distribution using least squares and artificial neural networks methods , 2015 .

[2]  T. Gregoire,et al.  A switching model of bole taper , 2001 .

[3]  U. Diéguez-Aranda,et al.  A merchantable volume system for Pinus sylvestris L. in the major mountain ranges of Spain , 2009, Annals of Forest Science.

[4]  A. Kozak,et al.  A variable-exponent taper equation , 1988 .

[5]  Sandhya Samarasinghe,et al.  Neural Networks for Applied Sciences and Engineering , 2006 .

[6]  Q. V. Cao,et al.  Prediction of tree diameter growth using quantile regression and mixed-effects models , 2014 .

[7]  David L. Olson,et al.  Advanced Data Mining Techniques , 2008 .

[8]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[9]  Mahadev Sharma,et al.  Modeling Stand Density Effects on Taper for Jack Pine and Black Spruce Plantations Using Dimensional Analysis , 2009, Forest Science.

[10]  A. Vahedi,et al.  Artificial neural network application in comparison with modeling allometric equations for predicting above-ground biomass in the Hyrcanian mixed-beech forests of Iran , 2016 .

[11]  C. López-Sánchez,et al.  Modelling and localizing a stem taper function for Pinus radiata in Spain , 2015 .

[12]  U. Diéguez-Aranda,et al.  Compatible taper function for Scots pine plantations in northwestern Spain , 2006 .

[13]  Maria J. Diamantopoulou.  Filling gaps in diameter measurements on standing tree boles in the urban forest of Thessaloniki, Greece , 2010, Environ. Model. Softw..

[14]  Mark J. Ducey,et al.  A stand density index for complex mixed species forests in the northeastern United States , 2010 .

[15]  David Scanlan,et al.  Graphics Processor Unit Hardware Acceleration of Levenberg- Marquardt Artificial Neural Network Training , 2013 .

[16]  U. Diéguez-Aranda,et al.  Aboveground stand-level biomass estimation: a comparison of two methods for major forest species in northwest Spain , 2012, Annals of Forest Science.

[17]  J. Gove,et al.  A comparison of alternative methods for estimating the self-thinning boundary line , 2005 .

[18]  G. Trincado,et al.  Predicting tree height from tree diameter and dominant height using mixed-effects and quantile regression models for two species in Turkey , 2018, Forest Ecology and Management.

[19]  A. Fernández-Landa,et al.  Non-destructive measurement techniques for taper equation development: a study case in the Spanish Northern Iberian Range , 2013, European Journal of Forest Research.

[20]  A. Robinson,et al.  Improving Taper Equations of Loblolly Pine with Crown Dimensions in a Mixed-Effects Modeling Framework , 2004, Forest Science.

[21]  Q. V. Cao,et al.  Evaluation of Methods for Calibrating a Tree Taper Equation , 2015 .

[22]  Robert S. Seymour,et al.  Regional stem taper equations for eleven conifer species in the Acadian Region of North America: development and assessment. , 2012 .

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

[24]  Dasheng Wu,et al.  Dynamic Estimation of Forest Volume Based on Multi-Source Data and Neural Network Model , 2015 .

[25]  T. Gregoire,et al.  Comparing strategies for modeling tree diameter percentiles from remeasured plots , 2008 .

[26]  Maria J. Diamantopoulou,et al.  Tree-bark volume prediction via machine learning: A case study based on black alder's tree-bark production , 2018, Comput. Electron. Agric..

[27]  Harold E. Burkhart,et al.  A Generalized Approach for Modeling and Localizing Stem Profile Curves , 2006, Forest Science.

[28]  G. Biging,et al.  Cumulative continuous predictions for bole and aboveground woody biomass in Eucalyptus globulus plantations in northwestern Spain , 2015 .

[29]  E. B. Görgens,et al.  Artificial Intelligence Procedures for Tree Taper Estimation within a Complex Vegetation Mosaic in Brazil , 2016, PloS one.

[30]  MehtätaloLauri,et al.  Evaluating marginal and conditional predictions of taper models in the absence of calibration data , 2012 .

[31]  Maria J. Diamantopoulou,et al.  Estimating Crimean juniper tree height using nonlinear regression and artificial neural network models , 2013 .

[32]  M. Diamantopoulou,et al.  Comparative study of standard and modern methods for estimating tree bole volume of three species in Turkey , 2008 .

[33]  Q. V. Cao,et al.  Calibrating fixed- and mixed-effects taper equations , 2011 .

[34]  Annika Kangas,et al.  Comparison of treewise and standwise forest simulators by means of quantile regression , 2008 .

[35]  Maria J. Diamantopoulou,et al.  Artificial Neural Network Models: An Alternative Approach for Reliable Aboveground Pine Tree Biomass Prediction , 2017 .

[36]  O. E. Sakici,et al.  STEM TAPER ESTIMATIONS WITH ARTIFICIAL NEURAL NETWORKS FOR MIXED ORIENTAL BEECH AND KAZDAĞI FIR STANDS IN KARABÜK REGION, TURKEY , 2018, CERNE.

[37]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[38]  Kevin N. Gurney,et al.  An introduction to neural networks , 2018 .

[39]  M. Diamantopoulou,et al.  Estimating tree bole volume using artificial neural network models for four species in Turkey. , 2010, Journal of environmental management.

[40]  A. Finkral,et al.  A New Look at Spread Rates of Exotic Diseases in North American Forests , 2010 .

[41]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[42]  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..

[43]  Q. V. Cao.  Calibrating a Segmented Taper Equation with Two Diameter Measurements , 2009 .

[44]  Charles O. Sabatia,et al.  On the Use of Upper Stem Diameters to Localize a Segmented Taper Equation to New Trees , 2015 .

[45]  R. Bailey,et al.  Compatible Volume-Taper Models for Loblolly and Slash Pine Based on a System with Segmented-Stem Form Factors , 2000, Forest Science.

[46]  R. G. Oderwald,et al.  Dimensionally compatible volume and taper equations , 2001 .

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

[48]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[49]  A. Cámara-Obregón,et al.  Fitting and Calibrating a Multilevel Mixed-Effects Stem Taper Model for Maritime Pine in NW Spain , 2015, PloS one.

[50]  Maria J. Diamantopoulou,et al.  The use of tree crown variables in over-bark diameter and volume prediction models , 2014 .

[51]  A. Kozak,et al.  My last words on taper equations , 2004 .

[52]  H. Akaike.  A new look at the statistical model identification , 1974 .

[53]  T. Gregoire,et al.  A geographically variable model of hemlock woolly adelgid spread , 2007, Biological Invasions.

[54]  S. Meng,et al.  Improved calibration of nonlinear mixed-effects models demonstrated on a height growth function. , 2009 .

[55]  O E Sakici,et al.  ARTIFICIAL INTELLIGENCE APPLICATIONS FOR PREDICTING SOME STAND ATTRIBUTES USING LANDSAT 8 OLI SATELLITE DATA: A CASE STUDY FROM TURKEY , 2018 .

[56]  W. Zeng,et al.  Height–diameter equations for larch plantations in northern and northeastern China: a comparison of the mixed-effects, quantile regression and generalized additive models , 2016 .