Amid the prevailing challenges of global climate change, the Brahmani River Basin emerges as an essential area of focus due to its significance and observed fluctuations in rainfall patterns. Our study employed the Adaptive Neuro-Fuzzy Inference System (ANFIS) to forecast these patterns, achieving commendable R-values of 0.90 during training and 0.87 during testing. This forecasted rainfall data, post calibration, was fed into the North American Mesoscale (NAM) and the Variable Infiltration Capacity (VIC) hydrological models. The VIC model, in particular, showcased R-values of 0.86 and 0.85 in its training and testing phases respectively. Furthermore, the forecasted rainfall was utilized to calculate runoff in a detailed water budget analysis for the Gomlai micro-catchment. Simultaneously, the spatial dynamics of the basin were unraveled through the Analytical Hierarchy Process (AHP), pinpointing the basin's specific discharge and recharge zones.
Our in-depth analysis unveiled a concerning trend of declining water discharge at the Gomlai station. When assessing the Gomlai micro-catchment, we confronted a significant water demand-supply gap: a demand of 252.06 Ham versus an available rainfall-runoff of 194.1 Ham, resulting in an annual water deficiency of 204.4 Ham. Moreover, the calibrated forecasted data was instrumental in attempting to determine the future flow behavior of the downstream reaches within the basin. In conclusion, this study not only brings to the forefront the hydrological challenges faced by the Brahmani River Basin but also offers strategic insights and interventions, suggesting its broader relevance and potential application in analogous regions and ecosystems.