Correcting sub-seasonal forecast errors with an explainable ANN to understand misrepresented sources of predictability of European summer temperatures

Sub-seasonal forecasts are challenging for numerical weather prediction (NWP) and machine learning models alike. Forecasting two-meter temperature (t2m) with a lead-time of two or more weeks requires a forward model to integrate multiple complex interactions, like oceanic and land surface conditions leading to predictableweather patterns. NWPmodels represent these interactions imperfectly, meaning that in certain conditions, errors accumulate and model predictability deviates from real predictability, often for poorly understood reasons. To advance that understanding, this paper corrects conditional errors in NWP forecasts with an artificial neural network (ANN). The ANN post-processes ECMWF extended-range summer temperature forecasts by learning to correct the ECMWF-predicted probability that monthly t2m in western and central Europe exceeds the climatological median. Predictors are objectively selected from ECMWF forecasts themselves, and from states at initialization, i.e. the ERA5 reanalysis. The latter allows the ANN to account for sources of predictability that are biased in the NWP model itself. We attribute ANN-corrections with two explainable AI tools. This reveals that certain erroneous forecasts relate to tropical west Pacific sea surface temperatures at initialization. We conjecture that the atmospheric teleconnection following this source of predictability is imperfectly represented by the ECMWF model. Correcting the associated conditional errors with the ANN improves forecast skill.