Assessing climatic influences on rodent density: a neural network modelling approach and a case study in Central Italy

In a climate change regime (observed in the past and forecasted for the future), it becomes more and more important to assess the role of the climatic environment in influencing the density of some species of interest. In this paper, using density data from Capture-Mark-Recapture (CMR) of Yellow-necked mouse (Apodemus flavicollis), we perform non-linear analyses and apply a neural network (NN) model (conceived for recognising links in complex systems) in order to establish which climatic parameters represent the driving forcing of rodent density in Central Italy. We discover direct and indirect climatic effects on this variable and, finally, a satisfying reconstruction of Yellow-necked mouse densities over the last 20 years is achived by a NN model. A further “hindcast” in the past (back to 1965) is performed by the model trained on a recent period and clear trends can be recognised in the record of reconstructed densities.