Tropical cyclones have become more destructive in the last decades due to increase in surface temperature as a result of global warming. Hurricanes/Tropical Cyclones are one of the costliest natural disasters globally because of the wide range of associated hazards. Hurricanes can cause upwards of 1000 deaths in a single event and are responsible for more than 100,000 deaths worldwide. During a tropical cyclone, humanitarian response efforts hinge on accurate risk approximation models that depend on wind speed measurements at different points in time throughout a storm’s life cycle.
Direct measurements of the winds within a tropical cyclone are sparse, particularly, over open ocean. Thus, diagnosing the intensity of a tropical cyclone is initially performed using satellite measurements. According to the National Hurricane Center (NHC), an accurate assessment of intensity using satellite data remains a challenge.
For several decades, forecasters have relied on visual pattern recognition of complex cloud features in visible and infrared imagery. However, visual inspection is manual, subjective and often leads to inconsistent estimates. This is the reason why we want to design and develop a system using Deep Learning and Machine Learning which predicts the hurricane’s speed using satellite images.