Historical Observations for Improving Reanalyses

Historical reanalyses have become a widely used resource for analyzing weather and climate processes and their changes over time. In this article I explore how further historical observations could support reanalyses and lead to products that reach further back in time or have a better quality. Using an off-line Ensemble Kalman Filter I estimate improvements arising from assimilating additional observations into the ensemble of the "Twentieth Century Reanalysis" Version 3 (20CRv3). I demonstrate this for three case studies and evaluate them using independent data and a leave-one-out approach. For Europe in 1807, assimilating additional pressure data improves the skill for pressure but slightly decreases it for temperature, while assimilating temperature data, a variable that is not assimilated in 20CRv3, improves the skill for temperature but slightly decreases it for pressure. Assimilating both leads to substantially increased skill in a leave-one-out approach. For Sub-Saharan Africa in 1877/78, assimilating ship-based pressure observations as well as land station data, albeit extremely sparse, leads to a slight improvement over the entire domain. Finally, for Europe in 1926/27, assimilating upper air and total column ozone observations both lead to improvements in geopotential height and wind in the middle troposphere and in total column ozone, but with little or no effect in the lower troposphere. This is because 20CRv3 is already close to perfect over Europe in this period. The article shows how additional observations could improve historical reanalyses. A backward extension to the 1780s seems possible, but further data rescue efforts are necessary. For some applications, improved fields as generated by the offline assimilation presented in this study could be useful.