Forecasting the maize yield of China's Jilin province from 1962 to 2004, with climate conditions and fertilizer as predictors, was investigated using multiple linear regression (MLR) and non-linear artificial neural network (ANN) models. Yield was set to be a function of precipitation from July to August, precipitation in September and the amount of fertilizer used. Fertilizer emerged as the dominant predictor and was non-linearly related to yield in the ANN model. Given the difficulty of acquiring fertilizer data for maize, the current study was also tested using the previous year's yield in the place of fertilizer data. Forecast skill scores computed under both cross-validation and retroactive validation showed ANN models to significantly outperform MLR and persistence (i.e. forecast yield is identical to last year's observed yield). As the data were non-stationary, cross-validation was found to be less reliable than retroactive validation in assessing the forecast skill.

The current paper aims to determine regional impacts of climate change on Irish farms examining the variation in farm responses. A set of crop growth models were used to determine crop and grass yields under a baseline scenario and a future climate scenario. These crop and grass yields were used along with farm-level data taken from the Irish National Farm Survey in an optimizing farm-level (farm-level linear programming) model, which maximizes farm profits under limiting resources. A change in farm net margins under the climate change scenario compared to the baseline scenario was taken as a measure to determine the effect of climate change on farms. The growth models suggested a decrease in cereal crop yields (up to 9%) but substantial increase in yields of forage maize (up to 97%) and grass (up to 56%) in all regions. Farms in the border, midlands and south-east regions suffered, whereas farms in all other regions generally fared better under the climate change scenario used in the current study. The results suggest that there is a regional variability between farms in their responses to the climate change scenario. Although substituting concentrate feed with grass feeds is the main adaptation on all livestock farms, the extent of such substitution differs between farms in different regions. For example, large dairy farms in the south-east region adopted total substitution of concentrate feed while similar dairy farms in the south-west region opted to replace only 0·30 of concentrate feed. Farms in most of the regions benefitted from increasing stocking rate, except for sheep farms in the border and dairy farms in the south-east regions. The tillage farms in the mid-east region responded to the climate change scenario by shifting arable production to beef production on farms.