Interactions among the red deer (Cervus elaphus, L.) population, meteorological parameters and new growth of the natural regenerated forest in Sneznik, Slovenia

Following a preliminary study (Stankovski et al., Ecol. Modelling, 108, 199 8), we use machine learning techniques to conduct a more detailed analysis of the interactions among the red deer population, meteorological parameter s and new forest growth. We use the machine learning program M5 (Quinlan, P roc. 10th Int. Conf. Machine Learning, Morgan Kaufmann, San Mateo CA, 1993) that learns regression trees to automate the modelling of dynamic interact ions. An area of 40 000 hectares of naturally regenerated forest on the hig h Dinaric Karst of Notranjska, Slovenia, is studied. The analysis uses data collected during the period 1976-1993, which include several meteorologica l parameters, the degrees of browsing intensity of new growth of woody plan ts (beech and maple), and parameters about the population of red deer. Mode ls of the degree of beech browsing and calf weight were studied earlier; he re, we automatically induce models of the red deer population size, the deg ree of beech and maple browsing, calf weight for 1- and 2-year-olds, and hi nd weight. The induced models are evaluated in terms of predictive accuracy and interpreted for their explanatory power. The models show that the mete orological parameters, the parameters of the red deer population and the ra tes of the browsing intensity of the new growth form a complex system with closely related parameters. While these interactions can be mainly explaine d by our current knowledge, we still gain some new knowledge from the autom atically induced models. The results emphasise the importance of a pluralis tic approach and a holistic perception of the system formed by meteorologic al conditions, the red deer population and the new growth in a forest ecosy stem. (C) 1999 Elsevier Science B.V. All rights reserved.