Accurate weather prediction is essential for mitigating the impacts of natural disasters, particularly in coastal areas vulnerable to cyclones and intense rainfall. This study aims to improve rainfall forecasting accuracy in cyclone-prone regions through a novel Interval Type-2 Fuzzy Logic System (IT2FLS) applied to Chennai, India, using data from 2013 to 2022. By leveraging IT2FLS with key meteorological parameters, the proposed IT2FLS framework uniquely addresses the inherent uncertainties in meteorological data, making it well-suited to handle real-time weather variability. The results obtained using IT2FLS are compared with the real data and the model’s performance is evaluated using the Root Mean Square Error (RMSE), Nash–Sutcliffe Efficiency (NSE), Quantile-Quantile (Q-Q) plot, Mean Absolute Error (MAE), and Mean Bias Error (MBE). These findings highlight IT2FLS’s capability to significantly enhance rainfall prediction accuracy, suggesting its potential as a valuable tool for disaster preparedness, risk management, and early warning systems in cyclone-prone regions.