Published Paper Details:

Cloudbursts are extreme localized rainfall events that occur within a short duration and often result in severe consequences such as flash floods, landslides,and significant damage to life and infrastructure. Traditional cloudburst prediction methods based on numerical weather prediction models face limitations in accurately forecasting such sudden and small-scale events due to their complex and non-linear nature. With the increasing availability of meteorological high-resolution data from satellites, Doppler radars, and ground-based weather stations, there is a growing need for advanced data-driven approaches that can effectively analyze these datasets for improved cloudburst prediction. This study focuses on integrating meteorological data with machine learning techniques to enhance cloudburst prediction accuracy. Various atmospheric parameters such as rainfall intensity, temperature, humidity, pressure, wind speed, and cloud characteristics are analyzed using machine learning and deep learning models including Random Forest, Support Vector Machines, and Long Short- Term Memory networks. The proposed approach aims to identify hidden patterns and early indicators of cloudburst events, providing timely and reliable predictions. The outcomes of this work contribute to the development of efficient early warning systems, supporting disaster risk reduction