Reliable forecasts of quasi-stationary, recurrent, and persistent large-scale circulation patterns – so-called weather regimes – are crucial for various sectors of society, including energy, health, and agriculture. Despite steady progress, probabilistic weather regime predictions still exhibit significant biases and are not reliable beyond 15 days lead time.

Thus, we aim to advance their predictions through post-processing of probabilistic forecasts. We adjust the multivariate probabilistic weather regime forecasts respective to their uncertainties and biases using a combination of statistical and machine learning methods to improve univariate and multivariate predictions and to incorporate exogenous variables as predictors.