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.

Abstract: Farm planning is based on awareness of climate variability, here assumed to depend on experience gained over the years, and to generate expectations on climatic variables. Expectations are based on probability distributions (pdfs) estimated on climate data and used to generate managing choices by means of Discrete Stochastic Programming. The model simulates the income losses in case farmers do not recognize the ongoing CC, and continue to plan assuming climate stability. In particular, the use of resources in 2010 is simulated based on the pdfs of the early 2000s, despite CC has changed the probabilities of the various states of nature. The model, calibrated with Positive Mathematical Programming, generates a 0.9% income increase when is allowed to adapt to 2010 climate pdfs. The model is also calibrated according to pdfs of 2010, i.e. recognizing CC: in this case income falls of 0.7% when farmers are simulated to use their soil mistakenly based of the 2000 pdfs. Given the short period of CC, the differences represent an appreciable error that farmers may be already committing. Properly specifying with the CC at local level can help building farmers’ awareness on it, and to properly manage their resources, recovering profitability.