One of the predominant processes of land cover change in the European Alps over the last 150 years has been the abandonment of agricultural land and the subsequent regeneration of forest. Here, we employed two sequential datasets from Switzerland (for the periods 1979-1985 and 1992-1997) to show how land-use and land cover data can be used to investigate such large scale ecological and land cover change processes. We applied a combination of generalized additive and generalized linear modelling to develop spatially explicit statistical models for land cover transitions between any of the following types: intensively used agricultural land, extensively used agricultural land, overgrown areas, open canopy forest, closed canopy forest. Climate, soil, relief-related data, basic socio-economic variables and information about the composition of the surrounding neighbourhood of the samples were utilised as potential predictors of land cover change. The proportion of variance explained differed considerably between models but a consistently high AUC for both calibration and evaluation datasets was achieved for the majority of the 25, with resulting values ranging from 0.58 to 0.96. The model residuals showed some degree of spatial autocorrelation despite the use of a sparse sampling regime and the inclusion of neighbourhood variables. We conclude that the analysis of sequential land cover datasets using the kind of statistical models developed here offers a promising way to investigate ecological processes such as forest succession at a large spatial scale.