Page menu:

Kachaev A. V., Petrov I. A., Kharuk V. I., Belova E. N. A New Approach to Developing a Logistic Regression Model Variables to Predict Tree Mortality, Based on Tree-Ring Growth Dynamics

dendrochronology, annual increment, Siberian stone pine Pinus sibirica du Tour, Khamar-Daban


UDC 630*11+57.087.1

How to cite: Kachaev A. V.1, Petrov I. A.2, Kharuk V. I.1, 2, Belova E. N.1 A new approach to developing a logistic regression model variables to predict tree mortality, based on tree-ring growth dynamics // Sibirskij Lesnoj Zurnal (Sib. J. For. Sci.). 2020. N. 5. P. … (in English with Russian abstract and references).

DOI: 10.15372/SJFS20200504

© Kachaev A. V., Petrov I. A., Kharuk V. I., Belova E. N., 2020

The annual tree increment is one of the integral indicators of abiotic and biotic processes occurring in the forest ecosystem. The use of logistic regression models based on annual tree-ring growth data is a promising approach to studying tree mortality. The diversity of logistic variables in scientific research is a result of various choices of statistics (average, median, growth trend, etc.) and their score in the time-window for the past N (5, 10, ... , 40) years. We propose a new scheme for the formation of logistic variables that involves fixing the statistics for calculating the average and choosing two non-intersecting time-windows based on measurements of the annual tree-rings growth. The choice of non-overlapping «windows» enables setting the ratio of the average growth of annual rings of trees between the windows for different periods of time. We examined the past 41 years of tree growth. Logistic regression models are constructed on a set of pairs of non-intersecting «windows» with a limit on the values of the sensitivity and specification of at least 1.6. The calculation of the percentage prediction if a tree is living or dying was done based on the contingency table in the logistic regression model. The logistic regression models were visualized using ROC curves. The models were compared on an expert scale based on the calculated area under the ROC curves. The obtained logistic regression model was verified by the bootstrap method. The calculations were carried out for the Siberian stone pine Pinus sibirica du Tour growing in the Baikal region (the Khamar-Daban Ridge) using the R programming language. The computed logistic regression model helped us predict live and dead trees in more than 80 % of cases.



Bigler C., Bugmann H. Growth-dependent tree mortality models based on tree rings // Can. J. For. Res. 2003. V. 33 N. 2. P. 210–221.

Cailleret M., Bigler C., Bugmann H., Camarero J. J., Cúfar K., Davi H., Mészáros I., Minunno F., Robert E. M., Suarez M. L., Tognetti R., Martínez-Vilalta J. Towards a common methodology for developing logistic tree mortality models based on ring-width data // Ecol. Appl. 2016. V. 26. Iss. 6. P. 1827–1841.

Das A. J., Battles J. J., Stephenson N. L., Mantgem P. J. van. The relationship between tree growth patterns and likelihood of mortality: a study of two tree species in the Sierra Nevada / Can. J. For. Res. 2007. V. 37 N. 3. P. 580–597.

Davis J., Goadrich M. The relationship between precision-recall and ROC curves // Proc. 23rd Int. Conf. Machine Learning. 2006. P. 233–240.

Greenwood D. L., Weisberg P. J. Density-dependent tree mortality in pinyon-juniper woodlands // For. Ecol. Manag. 2008. V. 255. N. 7. P. 2129–2137.

Hosmer D. W., Lemeshow S. Applied logistic regression. 2 ed. New York: J. Wiley & Sons, Inc., 2000. 375 p.

Kabakov R. I. R v deystvii. Analiz i vizualizatsiya dannykh v programme R / per. s angl. P. A. Volkovoy (R in action. Analysis and visualization of data in the program R / transl. from English P. A. Volkova). Moscow: DMK Press, 2014. 588 p. (in Russian).

Kachaev A. V. O vybore peremennykh v logisticheskikh regressionnykh modelyakh usykhaniya derevyev (Оn the choice of variables in logistic regression models of mortality of trees) // Lesnye ekosistemy borealnoy zony: bioraznoobrazie, bioekonomika, ekologicheskie riski. Mat-ly Vseros. konf. s mezhdunar. uchast. (Forest ecosystems of the boreal zone: biodiversity, bioeconomics, environmental risks. Proc. All-Rus. Conf. Int. Participat.). 2019. Р. 165–168 (in Russian with English abstract).

Kharuk V. I., Im S. T., Oskorbin P. A., Petrov I. A., Ranson K. J. Siberian pine decline and mortality in southern Siberian Mountains // For. Ecol. Manag. 2013. V. 310. P. 312–320.

Kharuk V. I., Im S. T., Petrov I. A., Dvinskaya M. L., Fedotova E. V., Ranson K. J. Fir decline and mortality in the southern Siberian mountains // Reg. Environ. Change. 2017a. V. 17. N. 3. P. 803–812.

Kharuk V. I., Im S. T., Petrov I. A., Golyukov A. S., Ranson K. J., Yagunov M. N. Climate-induced mortality of Siberian pine and fir in the Lake Baikal watershed, Siberia // For. Ecol. Manag. 2017b. V. 384. P. 191–199.

Malakhova E. G., Lyamtsev N. I. Rasprostranenie i struktura ochagov usykhaniya elovykh lesov Podmoskovya 2010–2012 godakh (Extent and structure of Moscow region spruce forest dieback in 2010-2012) // Izv. SPb. Lesotekh. akad. (Bull. St. Petersburg For. Acad.). 2014. Iss. 207. P. 193–201 (in Russian with English abstract).

Mastitskiy S. E., Shitikov V. K. Statistichesky analiz i vizualizatsiya dannykh s pomoshchyu R (Statistical analysis and data visualization using R). Moscow, 2014. 401 p. (in Russian).

Pavlov I. N. Bioticheskie i abioticheskie faktory usykhaniya khvoynykh lesov Sibiri i Dalnego Vostoka (Biotic and abiotic factors as causes of coniferous forests dieback in Siberia and Far East) // Sib. ekol. zhurn. (Sib. J. Ecol.). 2015a. V. 22. N. 4. P. 537–554 (in Russian with English abstract).

Pavlov I. N. Biotic and abiotic factors as causes of coniferous forests dieback in Siberia and Far East // Contemp. Probl. Ecol. 2015b. V. 8. N. 4. P. 440–456 (Original Rus. text © I. N. Pavlov, 2015, publ. in Sibirskij ekologicheskij zhurnal. 2015a. V. 22. N. 4. P. 537–554).

Rozenberg G. S. Ekologiya i fizika: paralleli ili seti? (v prodolzhenie diskussii) (Ecology and physics: parallels or network? (pending discussion)) // Biosfera (Biosphere). 2011. V. 3. N. 3. P. 296–303 (in Russian with English abstract).

Sarnatskiy V. V. Zonal’no-tipologicheskie zakonomernosti periodicheskogo massovogo usykhaniya el’nikov Belarusii (Zonal-typological patterns of periodic mass drying of spruce forests of Belarus) // Tr. BGTU (Proc. Belarus St. Technol. Univ.). N. 1. Lesn. khoz-vo (Forestry). 2012. V. 148. N. 1. P. 274–276 (in Russian with English abstract).

Scott M. L., Shafroth P. B., Auble G. T. Responses of riparian cottonwoods to alluvial water table declines // Environ. Manag. 1999. V. 23. P. 347–358.

Speer J. H. Fundamentals of tree-ring research. Tucson, AZ: Univ. Arizona Press, 2010. 368 p.

Vvedeniye v JSON (Introduction to JSON), 2019 (in Russian).

Zamolodchikov D., Kraev G. Vliyanie izmeneniy klimata na lesa Rossii: zafiksirovannye vozdeystviya i prognoznye otsenki (Influence of climate change on Russian forests: recorded impacts and forecast estimates) // Ustoychivoe lesopol’zovanie (Sustainable forest management). 2016. N. 4 (48). P. 23–31 (in Russian).

Return to list