Leveraging Machine Learning based Ensemble Time Series Prediction Model for Rainfall Using SVM, KNN and Advanced ARIMA+ E-GARCH

Today's precipitation is growing increasingly variable, making forecasting difficult. The Indian Meteorological Department (IMD) currently employs Composite and Stochastic approaches to forecast spring storm in Asia. As a corollary, planners are unlikely predict the macroeconomic effects of disasters (due excessive precipitation) or famine (less precipitation). amount that drops dependent on variety factors, including temperature atmosphere, humidity, velocity, mobility, weather conditions. This paper would then employ Hybrid time-series predictive ARIMA+ E-GARCH (Exponential Generalized Auto-Regressive Conditional Heteroskedasticity) precise runoff by taking into account different climatic considerations such as maritime tension, water content, relative dampness, min-max heat, heavy ice, geostrophic tallness, breeze patterns, soil barometric force. In perspective RMSE, MAE, MSE, proposed hybrid ARIMA+E-GARCH paradigm outperformed single simulations latest techniques.