Abstract/Summary

Multi-model combinations are a well established methodology in weather and climate prediction and their benefits have been widely discussed in the literature. Typical approaches involve combining the output of different numerical weather prediction (NWP) models using constant weighting factors, either uniformly distributed or determined through a prior skill assessment. This strategy, however, can lead to sub-optimal levels of skill as the performance of NWP models can vary with time (e.g., seasonally varying skill, changes in the forecasting system). Moreover, standard combination methods are not designed to incorporate predictions derived from sources other than NWP systems (e.g., climatological or time-series forecasts). New algorithms developed within the Machine Learning community provide the opportunity for `online prediction’ (also referred to as `sequential learning’). These methods consider a set of weighted predictors or `experts’ to produce subsequent predictions in which the combination or `mixture’ is updated at each step to optimize a loss or skill function. The predictors are highly flexible and can transparently combine both NWP- and statistically- derived forecasts. A set of these online prediction methods are tested and compared to standard multi-model combination techniques to assess their usefulness. The methods are general and can be applied to any model-derived predictand. A set of weather-sensitive European country-aggregate energy variables (electricity demand and wind power) are selected for demonstration purposes. Results show that these innovative methods exhibit significant skill improvements (i.e., between 5\% and 15\% improvement in the probabilistic skill) with respect to standard multi-model combination techniques for lead weeks up to 5. The incorporation of statistically-derived predictors (based on historical climate data) alongside NWP forecasts are also shown to contribute significant skill improvements in many cases.