Abstract: Sub Saharan Africa (SSA) is a region expected to be particularly sensitive to climate change effects on crop yield (Barrios et al. 2008). Annual precipitation, calculated as averages for each African country, is expected to change by −39 to +64 mm by 2030 (Jarvis et al. 2012). The effect of climate also becomes larger as ~97 % of all agricultural land in SSA is rain fed (Rockström et al. 2004). The aim of the ClimAfrica project (FP7) is to better understand and predict climate change in SSA and to analyse the impacts on ecosystems and populations. Within the modeling Work Package (WP3) the main goal is to quantify the sensitivity of vegetation productivity and water resources to seasonal interannual decadal variability in weather and climate using a set of crop models. Here we present some results on the sensitivity of  simulated carbon fluxes and FAPAR for different representations of cropland in a vegetation model (LPJ-GUESS: Lindeskog et al. 2013) as well as the sensitivity on simulated fluxes of carbon water and crop yield using a range of vegetation and crop models (LPJ-GUESS, LPJmL, ORCHIDEE and DSSAT), climate datasets, GCM output and bias correction/downscaling techniques.

Abstract: The Austrian regional case study in MACSUR extends the methods and builds upon the results of the CC-ILA project. CC-ILA enables cooperation between landscape planners and landscape ecologists to analyse mitigation and adaptation strategies for sustainable rural land use and landscape developments in a case study landscape. Subsequent research in MACSUR includes analysis towards rural development and the improvement of the climate impact data base for grasslands. The latter is achieved by collaborating with Crop-M partner LFZ Raumberg-Gumpenstein, who is able to utilize spill-overs within the Agromet-Monitor project.

Abstract: Statistical learning is a fairly new term referring to a set of supervised and unsupervised modelling and prediction techniques. It is based on traditional statistics but has been highly enhanced inspired by developments in machine learning and data mining. The main focus of statistical learning is to estimate the functions that quantify relations between several parameters and observed responses. These functions are further used for prediction, inference or a combination of both. For a particular case of quantitative responses, regularization techniques in regression are developed to overcome the weaknesses of ordinary least square (OLS) regression in prediction. These new shrinkage methods outperform OLS for prediction, especially in large datasets. In this study, a large dataset of field experiments on winter oilseed rape in Denmark for 22 years (1992 to 2013) was collected. Biweekly climatic data along with sowing date, harvest date, soil type and previous crop are considered as the explanatory variables. Yield of winter oilseed rape is considered as response variable. LASSO and Elastic Nets are the regularization techniques used to estimate the functions. Hold-one-out cross validation method for testing the prediction power reveals that these techniques are much useful in both prediction and inference. Since these techniques are included in recent versions of some software packages (e.g. R), they can be easily implemented by users at any level. The estimated function (model) is further used to predict the oilseed rape yield responses to climate change for several scenarios using representative weather data produced by a weather generator.