A new approach for seasonal prediction using the coupled model CFSv2 with special emphasis on Indian Summer Monsoon

Abstract Predicting Indian Summer Monsoon (ISM) is a challenging task due to its complexity and nonlinear interactions. Any improvement in the seasonal prediction skill of models would highly benefit a large population and the economy. In this context, three sets of hindcast experiments are carried out for 9 months each, for the period 1993–2019, using the National Centers for Environmental Prediction‐Climate Forecast System version 2 (NCEP‐CFSv2). The experiments differ from each other in the way they are initialized: one is initialized in February (FebIC), and the second in May (MayIC), whereas in the third one (Exp), ocean is initialized in February and allowed to evolve but the atmosphere reinitialized every month up to May. So, hindcasts of Exp are from the pre‐evolved ocean with realistic atmospheric initial conditions of May. The representation of mean tropical Indo‐Pacific Sea surface temperature (SST), Walker circulation, mean monsoon circulation and moisture transport to Indian landmass are better represented in Exp. The ISM rainfall prediction (interannual) skill improved in Exp as compared to FebIC and MayIC over central India, Indian land mass and extended monsoon region. The initialization strategy adopted in Exp reduces the model initial shocks especially in the upper ocean heat content and SST over the Indo‐Pacific region, thereby offering a cost‐effective alternative approach for reduction of the initial shock. The well‐known cold tongue SST bias over the equatorial Pacific in MayIC is reduced significantly in Exp with improved monsoon teleconnections and the overdependence of ISM rainfall on El Niño Southern Oscillation in MayIC is also reduced in Exp.