An ensemble-based approach to climate reconstructions

Data assimilation is a promising approach to obtain climate reconstructions that are both consistent with observations of the past and with our understanding of the physics of the climate system as represented in the climate model used. Here, we investigate the use of ensemble square root filtering (EnSRF) - a technique used in weather forecasting - for climate reconstructions. We constrain an ensemble of 29 simulations from an atmosphere-only general circulation model (GCM) with 37 pseudo-proxy temperature time series. Assimilating spatially sparse information with low temporal resolution (semi-annual) improves the representation of not only temperature, but also other surface properties, such as precipitation and even upper air features such as the intensity of the northern stratospheric polar vortex or the strength of the northern subtropical jet. Given the sparsity of the assimilated information and the limited size of the ensemble used, a localisation procedure is crucial to reduce 'overcorrection' of climate variables far away from the assimilated information.