Recent Advances in Tropical Cyclone Forecasting

Abstract

Tropical cyclones (TCs) are low-pressure weather phenomena characterized by a revolving circulation of high winds, heavy rain, and thunderstorms. TCs cause catastrophic damage if they make landfall in populated areas. Therefore, it is essential to monitor and prepare for potential disasters in the form of emergency responses or evacuations. For decades, predicting the intensity of tropical cyclones has been a challenging problem. The use of machine learning techniques to predict TCs is still challenging due to the number of parameters used for prediction and the availability of historical data. This paper highlights the techniques and parameters used to estimate TCs. This paper focuses on significant parameters such as ocean indices, sea surface temperature, and many others that have a greater impact on the formation of TCs. This paper discusses various opportunities and challenges in forecasting TCs in advance and the factors influencing the formation of TCs. The challenge is obtaining long amounts of historical data to analyse all ocean indices. Although many researchers have utilized ML techniques, the accuracy of TCs is still a more significant issue. Our survey focused on the importance of data fusion in accurately predicting TCs and their intensities.