Ramazan Özçelik

Estimating tree bole volume using artificial neural network models for four species in Turkey

Tree bole volumes of 89 Scots pine (Pinus sylvestris L.), 96 Brutian pine (Pinus brutia Ten.), 107 Cilicica fir (Abies cilicica Carr.) and 67 Cedar of Lebanon (Cedrus libani A. Rich.) trees were estimated using Artificial Neural Network (ANN) models. Neural networks offer a number of advantages including the ability to implicitly detect complex nonlinear relationships between input and output variables, which is very helpful in tree volume modeling. Two different neural network architectures were used and produced the Back propagation (BPANN) and the Cascade Correlation (CCANN) Artificial Neural Network models. In addition, tree bole volume estimates were compared to other established tree bole volume estimation techniques including the centroid method, taper equations, and existing standard volume tables. An overview of the features of ANNs and traditional methods is presented and the advantages and limitations of each one of them are discussed. For validation purposes, actual volumes were determined by aggregating the volumes of measured short sections (average 1 meter) of the tree bole using Smalians formula. The results reported in this research suggest that the selected cascade correlation artificial neural network (CCANN) models are reliable for estimating the tree bole volume of the four examined tree species since they gave unbiased results and were superior to almost all methods in terms of error (%) expressed as the mean of the percentage errors.

Modeling stem profile of Lebanon cedar, Brutian pine, and Cilicica fir in Southern Turkey using nonlinear mixed-effects models

The Max and Burkhart segmented taper model was fitted using nonlinear mixed-effects modeling techniques to account for within- and between-individual stem profile variation for Lebanon cedar (Cedrus libani A. Rich.), brutian pine (Pinus brutia Ten.), and cilicica fir (Abies cilicica Carr.) in Turkey. About 75% of the trees were randomly selected for model development, with the remainder used for model validation. Diameter measurements from various heights were evaluated for tree-specific calibrations by predicting random-effects parameters using an approximate Bayesian estimator. The procedure was tested with a validation dataset. Predictive accuracy of the model was improved by including random-effects parameters for a new tree based on upper stem diameter measurements. Prediction in stem diameter was less biased and more precise across the all sections of bole when compared to predictions based only on fixed-effects parameters. In the future, the proposed mixed models can be applied to region wide three species stands by fitting the model to a larger data set that more closely represents regional variation.

Compatible volume and taper models for economically important tree species of Turkey

Abstract• IntroductionThe accurate estimation of stem taper and volume are crucial for the efficient management of the forest resources. Compatible segmented polynomial taper and volume equations were developed for Brutian pine (Pinus brutia Ten.), Lebanon cedar (Cedrus libani A. Rich.), Cilicica fir (Abies cilicica Carr.), Scots pine (Pinus sylvestris L.), and Black pine (Pinus nigra Arnold.).• MethodsIn this study, the Clark et al. (USDA For Serv Res Pap SE-282, 1991) segmented taper model was selected as this model is one of the most tested segmented models and has frequently been well ranked for its excellent performance. The data for each species were divided into two sets: the majority (about 75%) was used to estimate model parameters, and the remaining data (about 25%) were reserved to validate the models. The performance of the models was compared and evaluated by average bias, standard error of the estimate (SEE), and a fit index (FI).• ResultsThe proposed model generally performed better than the other equations for the whole tree as well as for sections within the tree, based on the ten relative height classes examined. In addition, tree bole volume estimates were compared to other established tree bole volume estimation techniques.• ConclusionBased on our results, the taper equation of Clark et al. (1991) is recommended for estimating diameter at a specific height, height to a specific diameter, merchantable volume, and total volume for the species considered.

Estimating breast height diameter and volume from stump diameter for three economically important species in Turkey.

Abstract Predicting volume directly from stump dimensions is useful in many situations, such as timber trespass. In the present study, equations for predicting diameter at breast height (dbh) and tree volume from stump diameter outside bark were developed for three economically important tree species in the forest region of Bucak, Turkey. Diameter at breast height was estimated with relatively high accuracy using a simple linear model. Tree volume was estimated with high precision using an exponential equation. Weighted linear and non-linear least squares methods were used to consider heteroscedasticity observed in the volume–stump diameter relationships. The results of a non-linear extra sum of squares method and of the F test indicated that different equations are needed for estimating dbh and tree volume from stump diameter outside bark for different species.

Comparison of formulae for estimating tree bole volumes of Pinus sylvestris

Abstract Tree bole volumes of 103 Scots pine (Pinus sylvestris L.) were estimated using nine methods (paracone, centroid, control-variate with one and two measurement points, Hubers formula, antithetic method using importance sampling, standard volume table, local volume table, importance sampling using one and two measurement points, and a taper equation). These estimates were compared with “true” volume of each tree bole which was determined by aggregating the volumes of measured short sections (average 1m) using Smalians formula. The antithetic method performed well in terms of mean square error and tolerance intervals, which indicate the precision of the estimates. For both importance and control-variate sampling, better precision of the estimate may be achieved by taking measurements at two positions along a stem. The results showed that the antithetic method, importance sampling and control-variate method with two measurement points, paracone and centroid methods are useful alternatives to local volume tables and other standard formulae and are recommended for tree bole volume estimations of Scots pine in Turkey. However, in practice, convenience and economics play an important a role in the decision whether to use given estimation methods. On that basic, the paracone or centroid method may be recommended for use in tree volume estimating, as these are the easiest methods to apply, are less time consuming than other methods and show very acceptable statistical performance.

Accuracy using xylometry of log volume estimates for two tree species in Turkey

Abstract Water displacement (xylometry) was used to determine true volumes of 28 logs from Cilicica fir (Abies cilicica Carr.) and Brutian pine (Pinus brutia Ten.) trees ranging from 15 to 52 cm in diameter at breast height. Three methods were used with xylometry, measuring the increase in water level, the increase in weight of the xylometer or the decrease in weight of the object, and converting weight change to change in water volume. Traditional formulae (Huber, Smalian and Newton) and some recent methods and formulae (Bruce, overlapping bolts, Patterson–Doruska, the centroid and center of gravity) were used to estimate these volumes and the results were compared with the true values for both accuracy and precision. Comparison of these eight procedures for predicting log volumes of the two species tested showed that the centroid and center of gravity methods were less biased and provided better precision than other formulae and methods for estimating log volumes.

Desarrollo de una función de perfil mediante modelos mixtos para Pinus sylvestris en Turquía: selección de parámetros fijos a expandir

Las funciones de perfil predicen la variacion del diametro a lo largo del tronco del arbol, y se emplean, principalmente, para desarrollar tarifas de cubicacion con clasificacion de productos. En este trabajo se desarrollo una funcion de perfil para Pinus sylvestris en Turquia empleando la metodologia de modelos mixtos, donde algunos parametros del modelo incluyen una parte fija (comun a toda la poblacion) y un efecto aleatorio (especifico para cada individuo). Se analizaron diferentes estrategias para seleccionar la mejor combinacion de parametros fijos a expandir con efectos aleatorios (parametros de efectos mixtos): (1) aquellos parametros fijos que presentaron mayor variabilidad y (2) todas las posibles combinaciones de uno y dos parametros de efectos mixtos, resultando esta ultima mas adecuada. Dado que la inclusion de efectos aleatorios no fue suficiente para considerar la autocorrelacion de residuos, se modelizo la matriz de varianza-covarianza del termino de error mediante una estructura autorregresiva de primer orden. Tambien se evaluo la respuesta calibrada (estimacion de los efectos aleatorios para un nuevo individuo) utilizando un diametro medido a distintas alturas a lo largo del tronco. El modelo mixto seleccionado presento los mejores resultados en las fases de ajuste y de calibracion. En general, se recomienda emplear el modelo mixto si se dispone de una medicion adicional del diametro del tronco a una altura de entre 40-90 % de la altura total del arbol. En caso contrario, desde un punto de vista predictivo resulta mas conveniente emplear el modelo ajustado por minimos cuadrados ordinarios.

Toros göknarında gövde çapı modelinin doğrusal olmayan karışık etkili modelleme yaklaşımı ile geliştirilmesi

The Max and Burkhart segmented taper equation was fitted using nonlinear mixed-effects modeling techniques to account for within- and between-individual variation in Taurus fir (Abies cilicica Carr.) stem profiles. Totally 327 sample trees measured and about 60% (203 trees) of the trees were randomly selected for model development and the reminder 40% (124 trees) of the trees used for model validation. Based on goodness-of-fit criteria, the model including three random-effects parameters β1, β3, and β4 was the best. An error variance function and a continuous auto correlation structure incorporated in model to within and between-tree residual variances and spatial autocorrelation between residuals. However, most of the residual autocorrelation was accounted for by including random effects. Upper stem diameter measurements were used to estimate random effects parameters using an approximate Bayesian estimator, which localized stem profile curves for individual trees. The procedure was tested with a validation data set. The goodness-of-fit statistics (Bias, precision, and RMSE) showed that upper stem diameter measurements and subsequent estimates of random effects improved the predictive capability of the taper equation mainly in the lower portion of the bole. Accordingly results of this research, there is no big differences between one and two additional upper stem diameter measurements for predictive capability of model. The method can localize stem curves for trees growing under different site and management conditions in natural Taurus fir stands. The results of this study support previous findings that mixed-effect modeling approach increases flexibility and efficiency of taper equations for upper stem diameter prediction.

Tree-bark volume prediction via machine learning: A case study based on black alder’s tree-bark production

Abstract Tree-bark volume estimation is a multi-faceted problem and at the same time of vital importance in the area of forest resources management. This importance relies on the fact that it constitutes a key variable for accurately assessing timber quantities, while at the same time its use has been spread as a soil-covering product or as a soil fertilizer or as a substitutional medicinal product. Consequently, due to its substantial economic impact, the accurate prediction of the tree-bark volume is of utmost importance. In this study, we propose three bark volume prediction models for black alder trees (Alnus glutinosa (L.) Gaertn subsp. barbata (C.A. Mey.) Yalt.) each targeting a different creation source of the black alder forest. Hence, we used data from naturally regenerated, plantation and coppice stand types. 1334 stem analysis data were collected for three different stand types. Two different modeling techniques were used, the weighted nonlinear regression and the e-support vector regression techniques. These two modeling approaches were selected due to the fact that the need to handle regression analysis problems (noise in the data, high variability and/or non-normal distributions) is essential. The state-of-the-art approach suggests the usage of machine learning techniques in an effort to build reliable and robust models able to deal with complex environmental problems. An overall illustration of the precision obtained by the constructed models was conducted by statistical criteria such as the root mean square error, the correlation coefficient, the Furnival’s index of fit and the Akaike’s information criterion. Although the estimation and prediction errors of the two different modeling techniques seem to be close in pure numbers, the e-support vector regression models gave the most accurate results for all stand types as compared to the nonlinear regression. Based on the results obtained from this study, the constructed e-support vector regression models for modeling tree-bark volume showed a great ability to generalize, and thus worth considering as an alternative to regression modeling that enables increasing our ability for successful forest management.

Modeling of stem taper model with mixed effects approach for oriental spruce

Dogu ladini (Picea orientalis L.) ulkemizin onemli agac turlerinden birisidir. Bu nedenle, ladin ormanlarinin bugun ve gelecege donuk yonetim ve planlama stratejilerinin gelistirilmesinde, turun buyume ve hasilatina iliskin bilgilere ihtiyac duyulmaktadir. Ormanlarin buyume ve hasilatina iliskin tahminlerde kullanilan en onemli yapi taslarindan birisi, agac hacim tahminleridir. Govde capi denklemleri, bir agaca iliskin toplam ve ticari hacim tahminlerinde en guvenilir ve dogru yaklasimlardan biri olarak kabul edilmektedir. Bu calismada, Ardahan-Posof Yoresi dogu ladini mescerelerinden elde edilen 170 agac kullanilarak dogrusal olmayan karisik etkili modelleme (NLME) yaklasimi ile govde capi modeli gelistirilmistir. Karisik etkili modelleme, bir agacin kendi icinde ve agaclar arasinda govde formu acisindan degisimin hesaplanmasina imkân saglamaktadir. Calismanin birinci asamasinda, oncelikle hangi parametrelerin tesadufi etkili parametrelerle genisletilmesi gerektiginin ortaya konmasi icin modelin bir ve iki parametresine tesadufi parametreler eklenerek olasi tum kombinasyonlar test edilmistir. Modele tesadufi etkili parametrelerin eklenmesi ayni agac icin elde edilen hatalar arasinda var olan korelasyonun hesaplanmasi icin yeterli olmamis, hata terimine iliskin varyans-kovaryans matrisi birinci derece otoregresif hata yapisi AR(1) ile modellenmistir. Karisik etkili modele AR(1)’in eklenmesi ile hatalar arasindaki otokorelasyonun tamaminin uzaklastirilmasi mumkun olmustur. Ikinci asamada, govde uzerinde farkli noktalarda olculen cap degerleri kullanilarak kalibrasyon sonuclari degerlendirilmistir. Secilen karisik etkili model, hem model gelistirme hem de kalibrasyon icin en iyi sonuclari uretmistir. Genel olarak, kalibrasyon icin toplam boyun %40-80 arasinda olculen ekstra caplarin govde capi modelinin tahmin performansini arttirdigi gozlenmistir. Sonuc olarak model kalibrasyonu, karisik etkili model seciminde onemli bir kriter olarak goz onunde bulundurulmalidir.