A Cloud Native Machine Learning based Approach for Detection and Impact of Cyclone and Hurricanes on Coastal Areas of Pacific and Atlantic Ocean


Students, Drumil Joshi, Fawzan Sayed, Harsh Jain, Jai Beri, Faculty, Yukti Bandi, Dr. Sunil Karamchandani
Dwarkadas J Sanghvi College of Engineering, Department of Electronics and Telecommunication Mumbai, India.


Tropical Storms are one of the most dangerous natural disasters known to man. The concept of predicting these has been around for as long as they have existed. Improvements are made to reduce the error using newer techniques or better processes. In this research paper, we are trying to predict the occurrence of storms from the Pacific and the Atlantic Oceans on American land. The data is used to train various machine learning models and comparison is drawn between them to conclude the best for our application. The results are then shown on a map to get a visual representation using the folium library. The entire project is also deployed using Microsoft Machine Learning Azure to help with deployment over the web service. This paper hopes to present a system that accurately predicts and efficiently presents everything regarding the real-time occurrence of hurricanes and typhoons.