MODELING THE POPULATION-DYNAMICS OF RED DEER (CERVUS-ELAPHUS L.) WITHREGARD TO FOREST DEVELOPMENT

Recent advances in artificial intelligence in general: and in machine learning in particular, enable scientists to apply new machine learnin g technics to their specific areas. In our work we apply such a machin e learning technique to the modelling of population dynamics of red de er for the 40000 hectares co-natural manage forest area on high Karst of Notranjska in Slovenia. We used the RETIS program, a machine learni ng tool developed by A. Karalie at the Institute Jozef Stefan in Ljubl jana. This program induces regression trees from data, and has already been applied to several ecological problems. RETIS was applied on dat a, collected in the period 1976-1994, which included several meteorolo gical parameters, parameters about the state of the forest, and parame ters about the population of the red deer. Given these data about the observed system, the system RETIS automatically induces a model which has the form of a regression tree. We evaluate our induced models qual itatively and quantitatively. For the qualitative evaluation, we prese nt an expert interpretation of the models. We show that quantitatively , using the models (we use a relative prediction error) and given the meteorological parameters during winter and summer and an estimate of the number of red deer in the area, it is possible to predict the stat e of the forest in the near future. This is very important for maintai ning the balance between red deer population and other parameters of t he forest, which will allow sustainable development of the complex for est ecosystem. (C) 1998 Elsevier Science B.V. All rights reserved.