Cloud Burst Prediction System using Machine Learning
Herin Shani. S, G. Nagappan · 2024
This abstract presents an innovative approach that leverages the Gramian Angular Field (GAF) in conjunction with Convolutional Neural Networks (CNN) to improve the accuracy and reliability of cloudburst prediction systems. The utilization of GAF and CNN represents a breakthrough in modeling the complexities inherent in meteorological data. GAF, with its generative capabilities, constructs synthetic data closely resembling the underlying meteorological distributions. CNN, renowned for its proficiency in spatial data analysis, is adept at recognizing intricate patterns within meteorological images. The application of GAF and CNN in cloudburst prediction systems signifies a significant advancement in the field. By effectively recognizing and generating synthetic data representative of meteorological complexities, this approach has the potential to significantly improve the precision and lead time of cloudburst predictions, thereby enhancing early warning systems and disaster preparedness.