Spatial Variation of Drivers of Agricultural Abandonment with Spatially Boosted Models

Agricultural abandonment (AA) is a significant land use process in the European Union (EU) and modeling its driving factors has great scientific and policy interest. Past studies of drivers of AA in Europe have been limited by their restricted geographic regions and their use of traditional statistical methods, which fail to consider the spatial variation in both predictors and AA itself. In this study, we implement a modeling framework based on boosted classification with spatially-varying terms, choosing the squared loss function and P-splines as base learners for their mathematically superior properties. By comparing models containing both constant and spatially-varying coefficients, we find telling spatial trends in the relationship between the drivers and AA that can be used to inform international policies for agriculture.