High-latitude volcanic eruptions in the Norwegian Earth System Model: the effect of different initial conditions and of the ensemble size

Large volcanic eruptions have strong impacts on both atmospheric and ocean dynamics that can last for decades. Numerical models have attempted to reproduce the effects of major volcanic eruptions on climate; however, there are remarkable inter-model disagreements related to both short-term dynamical response to volcanic forcing and long-term oceanic evolution. The lack of robust simulated behaviour is related to various aspects from model formulation to simulated background internal variability to the eruption details. Here, we use the Norwegian Earth System Model version 1 to calculate interactively the volcanic aerosol loading resulting from SO2 emissions of the second largest high-latitude volcanic eruption in historical time (the Laki eruption of 1783). We use two different approaches commonly used interchangeably in the literature to generate ensembles. The ensembles start from different background initial states, and we show that the two approaches are not identical on short-time scales (<1 yr) in discerning the volcanic effects on climate, depending on the background initial state in which the simulated eruption occurred. Our results also show that volcanic eruptions alter surface climate variability (in general increasing it) when aerosols are allowed to realistically interact with circulation: Simulations with fixed volcanic aerosol show no significant change in surface climate variability. Our simulations also highlight that the change in climate variability is not a linear function of the amount of the volcanic aerosol injected. We then provide a tentative estimation of the ensemble size needed to discern a given volcanic signal on surface temperature from the natural internal variability on regional scale: At least 20-25 members are necessary to significantly detect seasonally averaged anomalies of 0.5 degrees C; however, when focusing on North America and in winter, a higher number of ensemble members (35-40) is necessary.