Reliability Ensemble Averaging of 21st century projections of
terrestrial net primary productivity reduces global and regional
uncertainties
Abstract. Multi-model averaging techniques provide opportunities to extract additional information from large ensembles of simulations. In particular, present-day model skill can be used to evaluate their potential performance in future climate simulations. Multi-model averaging methods have been used extensively in climate and hydrological sciences, but they have not been used to constrain projected plant productivity responses to climate change, which is a major uncertainty in earth system modelling. Here, we use three global observation-orientated estimates of current net primary productivity (NPP) to perform a reliability ensemble averaging (REA) using 30 global simulations of the 21st century change in NPP based on the Inter-Sectoral Impact Model Intercomparison Project (ISI-MIP) business as usual emissions scenario. We find that the three REAs support an increase in global NPP by the end of the 21st century (2090s) compared to the 2000s, which is 4–6 % stronger than the ensemble ISIMIP mean value of 23.7 Pg C y−1. Using REA also leads to a 43–67 % reduction in the global uncertainty of 21st century NPP projection, which strengthens confidence in the resilience of the CO2-fertilization effect to climate change. This reduction in uncertainty is especially clear for boreal ecosystems. Conversely, the large uncertainty that remains on the sign of the response of NPP in semi-arid regions points to the need for better observations and model development in these regions.