broj: 9-10/2019        pdf (7,03 MB)



HR EN

                    stari brojevi      novi broj

Znanstveno-stručno i staleško glasilo
Hrvatskoga šumarskoga društva
Journal of Forestry Society of Croatia
      Prvi puta izašao 1877. godine i neprekidno izlazi do današnjeg dana
   ISSN No.: 0373-1332              UDC 630* https://doi.org/10.31298/sl
upute autorima
WEB EDITION
ARHIVA ČASOPISA


HRČAK


 
EDITORIAL
     
Uredništvo
Will a change in the ministry bring about a changein the attitude towards the forestry profession?     pdf     HR     EN 389
 
ORIGINAL SCIENTIFIC PAPERS
     
Damir Ugarković, Željko Španjol, Ivica Tikvić, Dražen Kapučija, Ivana Plišo Vusić UDK 630* 111 (001)
https://doi.org/10.31298/sl.143.9-10.1
Microclimate differences in the degradation stages of holm oak (Quercus ilex L.) forests     pdf     HR     EN 391
Ivan Lukić, Nikola Lacković, Milan Pernek, Christa Schafellner UDK 630* 453 (001)
https://doi.org/10.31298/sl.143.9-10.2
Redefinition of critical numbers of gypsy moth (Lymantria dispar L.) egg masses for pedunculate oak (Quercus robur L.) and first calculation for common beech (Fagus sylvatica L.) in Republic of Croatia     pdf     HR     EN 403
Muammer Şenyurt, Ilker Ercanli UDK 630* 524 (001)
https://doi.org/10.31298/sl.143.9-10.3
A comparison of artificial neural network models and regression models to predict tree volumes for crimean black pine trees in Cankiri forests     pdf     HR     EN 413
Abstract
In this study, it is aimed to use and compare Artificial Neural Network (ANN) models for predicting individual tree volumes for of Crimean Black Pine trees within the Cankiri Forests. The single and double entry-volume equations and the Fang et al. (2000)’s compatible volume equation based on the classical and traditional methods were used by 360 Crimean Black Pine trees to obtain these tree volume predictions. To determine the best predictive alternative for ANN models, a total of 320 trained networks in the Multilayer Perceptron (MLP) and a total of 20 trained networks in the Radial Basis Function (RBF) architectures was trained and used to obtain the individual tree volume predictions. On the basis of the goodness-of-fit statistics, the ANN-based on MLP 1-9-1 including dbh as an input variable for single entry volume predictions showed a better fitting ability with SSE (2.7763), (0.9339), MSE (0.00910), RMSE (0.0954), AIC (-823.25) and SBC (-1421.81) than that by the other studied volume methods including dbh as an explanatory variable. For double entry volume predictions, including dbh and total height as input variables, ANN based on MLP 2-15-1 resulted in better fitting statistics with SSE (0.8354), (0.9801), MSE (0.00274), RMSE (0.0523), AIC (–579.55) and SBC (–1788.11).

Key words: Tree Volume Prediction; Artificial Neural Network; Single and double volume equations; Segmented taper equation
Tomislav Sedlar, Tomislav Sinković, Ivana Perić, Andrej Jarc, Srđan Stojnić, Bogoslav Šefc UDK 630* 812 (001)
https://doi.org/10.31298/sl.143.9-10.4
Hardness of thermally modified beech wood and hornbeam wood     pdf     HR     EN 425
 
PRELIMINARY COMMUNICATION
     
Anamarija Jazbec, Mislav Vedriš, Ksenija Šegotić UDK 630*945
https://doi.org/10.31298/sl.143.9-10.5
Analysing the duration of studyng on undergraduate studies et the Faculty of forestry, University of Zagreb     pdf     HR     EN 435
Jelena Nedeljković, Mirjana Stanišić, Dragan Nonić, Mersudin Avdibegović, Marta Curman, Špela Pezdevšek Malovrh UDK 630* 111
https://doi.org/10.31298/sl.143.9-10.6
Climate change governance in forestry and nature conservation: institutional framework in selected see countries     pdf     HR     EN 445
 
PROFESSIONAL PAPERS
     
Ivana Plišo Vusić, Irena Šapić, Joso Vukelić UDK 630* 181.6 + 187
https://doi.org/10.31298/sl.143.9-10.7
Identification and mapping of Natura 2000 forest habitat types in Croatia (II) – 91F0, riparian mixed forests of Quercus robur, Ulmus laevis, Ulmus minor and Fraxinus angustifolia; 91L0, Oak-hornbeam forests of the illyrian area     pdf     HR     EN 461
Damir Drvodelić, Igor Poljak, Ivan Perković, Mario Šango, Katarina Tumpa, Ivana Zegnal, Marilena Idžojtić UDK 630* 232.3
https://doi.org/10.31298/sl.143.9-10.8
Laboratory germination testing of the sweet chestnut (Castanea sativa Mill.) according to ISTA rules     pdf     HR     EN 469

                UNDER CONSTRUCTION