The proposition of a new algorithm facilitates the predictability of weak/strong monsoons that lead to drought/flood events, respectively, in the Indian summer monsoon rainfall (ISMR). The proposed method estimates skewed Gaussian kernel distribution in the extreme values extracted from the rainfall series, and confidence levels of drought and flood years are obtained using bootstrap. Using the selected Coupled Model Intercomparison Phase 5 (CMIP5) simulations under representative concentration pathways (RCP) 8.5 scenario, the proposed method detects that extreme droughts (at 99% confidence level) in India are likely to occur in 2024 and 2027 in the early 21st century. Similarly, models project that 2031, 2032, and 2033 will be the most prominent flood years. It is projected that the probability of drought occurrence is likely to increase by 16%. In contrast, it is expected to diminish flood events by 11% in the future under projected global warming. Notably, our analysis reveals that 23.4% of grids covering ~30% of the Indian region are likely to experience increased frequency and intensity of droughts during 2020–2029, mainly covering the Northeast, Central, and Southern India. Furthermore, during this period, the Northeast and some parts in the North would experience floods over 29.6% (which covers ~ 39%) of the total grids. The proposed algorithm may be used for drought and flood monitoring over any geographical terrain.