A simple statistical technique to improve seasonal predictions of northeast monsoon rainfall over India using selective ensemble mean.

The predictability of northeast monsoon rainfall (NEMR) has been poorly studied. It is noted that the September-initialized multi-model ensemble (MME) of seasonal forecast systems shows modest skill in predicting NEMR over the southern peninsula of India for the October-November-December (OND) season. This study proposes an approach to improve forecast skill by selecting MME members that effectively capture the correlation between NEMR and the major modes of tropical climate variations (viz., El Niño-Southern Oscillation and Indian Ocean Dipole) during the OND season. Both deterministic and probabilistic verification results indicate that the selected ensemble outperforms the full MME in predicting NEMR, with the improved skill. The improvement can be attributed in part to the improved external forcing due to the sea surface temperature and to the realistic representation of the atmospheric processes in the ensemble of selected members. Composite analysis of extreme positive and negative precipitation seasons over the NEMR region shows the ensemble of selected members to capture the precipitation and streamfunction anomalies realistically. The MME failed to capture the correct phases of precipitation and streamfunction anomalies due to unrealistic atmospheric response to precipitation anomalies in the equatorial Pacific.