Abstract: Climate change is expected to lead to yield reductions in cereals due to effects on both growth duration and physiological processes affecting assimilation and translocation to grains. However, some of these negative effects may be alleviated through plant breeding. A pot experiment with selected spring wheat varieties exposed to post anthesis heat stress (35 oC for 5 days) showed that the major factor affecting variety differences in heat tolerance was related to effects on green leaf area duration after heat stress. A field experiment with the same selected spring wheat varieties showed large differences between the varieties in crop development and in biomass. The data were used to calibrate the FASSET and Sirius crop models using a sequenced calibration procedure. Both models simulated crop growth and yield well. A sensitivity analysis with increasing temperature showed declining yields for both models with higher rates of yield reduction at temperature increases above 3oC. The models agreed on the pattern of yield decline between cultivars, with larger yield declines being related to earliness. The FASSET model was further modified to simulate effects of cultivar differences in remobilization of water soluble carbohydrates and effects of post-anthesis heat stress on crop yield. Effects of variation in threshold temperature for heat stress as well as response rate are tested.

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.