Combined TBATS and SVM model of minimum and maximum air temperatures applied to wheat yield prediction at different locations in Europe

•The combined SVM/TBATS model improves pure TBATS or SVM air temperature prediction.•Dynamics of the weather conditions influences SVM/TBATS long-term prediction.•The lengths of the learning/testing data sets should be individually estimated.•The SVM/TBATS model can be successfully used for filling gaps in time series data.•SVM/TBATS predicted and measured temperature values lead to similar modelled yield.