Cyclone Prediction Visualization Tools Using Machine Learning Models and Optical Flow

Abstract

A tropical cyclone is one of the most egregious natural disasters in the world that brings calamity to coastal lives by hitting the corresponding country's bordering basins since ancient time. The rapid intensification of TC has always been a threat to the coastal peoples living in different corners of the world. Geographical locations and geographical settings of being a low-lying deltaic country could trigger this calamitous event and bring individual hazards like a storm surge, inundation, oceanic flood, and many more. Tracking a tropical cyclone is not an easy task as it shows nonlinear behavior to different models to forecast. However, considering several limitations, experts from different countries use several products like satellite images, numerical data, and radar images to predict the formation, track, and the intensity of a cyclone. However, it is concerning that a full-fledged automatic cyclone prediction visualization tool for the wider populace does not exist. In this work, we are unlikely to provide an absolute automated visualization tool. Rather, we attempted to compensate for the lack of one by creating a prototype of a cyclone prediction and visualization dashboard with Streamlit, a Python framework for rapidly developing machine learning web apps. Furthermore, we considered visualizing the data sets in order to interpret them from various perspectives, and we used optical flow to determine the cyclonic behaviors as another approach.