The status of the brown bear (Ursus arctos) in Spain has suffered a dramatic decline during the last centuries, both in area and numbers. Current relict populations are suspected to be under immediate risk of extinction. The aim of our model is to attain an understanding of the main processes and mechanisms determining population dynamics in the Cordillera Cantabrica. We compile the knowledge available about brown bears in the Cordillera Cantabrica, northern Spain, and perform a population viability analysis (PVA) to diagnose the current state of the population and to support current management. The specially constructed simulation model, based on long-term field investigations on the western brown bear population in the Cordillera Cantabrica, includes detailed life history data and information on environmental variations in food abundance. The method of individual-based modeling is employed to simulate the fate of individual bears, Reproduction, family breakup, and mortalities are modeled in annual time steps under the influence of environmental variations in food abundance, mortality rates, and reproductive parameters. In parallel, we develop an analytical model that describes the mean behavior of the population and that enables us to perform a detailed sensitivity analysis. We determine current population parameters by iterating the model with plausible values and compare simulation results with the 1982-1995 time pattern of observed number of females with cubs of the year. Our results indicate that the population suffered a mean annual decrease of similar to 4-5% during the study period, 1982-1995. This decrease could be explained by a coincidence of high poaching pressure with a series of climatically unfavorable years during the period 1982-1988. Thereafter, population size probably stabilized. We estimate that the population currently consists of 25 or 26 independent females and a total of 50-60 individuals. However, our viability analysis shows that the population does not satisfy the criterion of a minimum viable population if mortalities remain at the level of the last few years of 1988-1995. The "salvation" of at least one independent female every three years is required. The population retains relatively high reproductive parameters, indicating good nutritive conditions of the habitat, but mortality rates are higher than those known in other brown bear populations. The most sensitive parameters, adult and subadult mortality of females, form the principal management target. Our model shows that the series of females with cubs contains valuable information on the state of the population. We recommend monitoring of females with cubs as the most important management action, both for collecting data and for safeguarding the most sensitive part of the population.
