AUTHOR=Carvalho-Oliveira Julianna , Borchert Leonard F. , Zorita Eduardo , Baehr Johanna 

TITLE=Self-Organizing Maps Identify Windows of Opportunity for Seasonal European Summer Predictions

JOURNAL=Frontiers in Climate

VOLUME=Volume 4 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/climate/articles/10.3389/fclim.2022.844634

DOI=10.3389/fclim.2022.844634

ISSN=2624-9553

ABSTRACT=We combine a machine learning method and ensemble climate predictions to investigate
windows of opportunity for seasonal predictability of European summer climate associated with the North Atlantic jet stream. We particularly focus on the impact of North Atlantic spring sea surface temperatures (SST) on the four dominant atmospheric teleconnections associated with the jet stream: the summer North Atlantic Oscillation in positive and negative phases, the Atlantic Ridge, and Atlantic Low. We go beyond standard forecast practices by not only identifying these atmospheric teleconnections and their sea surface temperature precursors, but by making use of these identified precursors in the analysis of a dynamical forecast ensemble. Specifically, we train the neural network-based classifier Self-Organising Maps (SOM) with ERA-20C reanalysis and combine it with model simulations from the Max Planck Institute Earth System Model in mixed resolution (MPI-ESM-MR). We use two different sets of 30-member hindcast ensembles initialised every May, one for training and evaluation between 1902-2008, and one for verification between 1980-2016, respectively. Among the four summer atmospheric teleconnections analysed here, we find that Atlantic Ridge simulated by MPI-ESM-MR shows the best agreement with ERA-20C, thereby representing with its occurrence windows of opportunity for skillful summer predictions. Conversely, Atlantic Low shows the lowest agreement, which might limit the model skill for early warning of warmer than average summers. In summary, we find that spring SST patterns identified with a SOM analysis can be used to guess the dominant summer atmospheric teleconnections at initialisation and guide a sub-selection of potential skillful ensemble members. This holds especially true for Atlantic Ridge and Atlantic Low, and is unclear for summer NAO. We show that predictive skill in the selected ensemble exceeds that of the full ensemble over regions in the Euro-Atlantic domain where spring SST significantly correlates with summer SLP. In particular, we find a significant improvement in predictive skill for SLP, geopotential height at
500 hPa, and 2 metre temperature at 3-4 months lead time over Scandinavia, which is robust
among the two sets of hindcast ensembles.