Improving the prediction of the Madden–Julian Oscillation of the ECMWF model by post-processing

Abstract. The Madden–Julian Oscillation (MJO) is a major source of predictability on the sub-seasonal (10 to 90 d) timescale. An improved forecast MJO may have important socioeconomic impacts due influence both tropical and extratropical weather extremes. Although in last decades state-of-the-art climate models proved their capability for forecasting exceeding 5-week prediction skill, there still room improving prediction. In this study we use multiple linear regression (MLR) machine learning (ML) algorithm as post-processing methods improve model that currently holds best performance, European Centre Medium-Range Weather Forecasts (ECMWF) model. We find MLR ML outperforms MLR. largest improvement geographical location intensity.