Hurricanes follow a generalized life cycle based on wind speed(wind-speed minimum 119km/h).The ”Saffir-Simpson Hurricane Wind Scale” is a 1 to 5 rating based on a hurricane’ssustained wind speed. This scale estimates potential property damage. Hurricanes havingcategory 3 and higher are considered major hurricanes because of their potential for significantloss of life and damage. Category 1 and 2 hurricanes are still dangerous, however, and requirepreventative measures. Therefore here the main goal is to predict the number of the hurricanesof the particular category that are expected to take place in given inputted year.This can beutilized to make skillful forecasts so with that precautions can be taken to protect from the damage.

Principal Component Analysis (PCA) is an unsupervised, non-parametric statisticaltechnique primarily used for dimentionality reduction in machine learning.High dimen-tionality means that the dataset has a large number of features. The primary problemassociated with high-dimensionality in the machine learning field is computation com-plexity. Also dimentionality reduction helps in proper data visualisation. In our caseprediction is the time sensitive. As quick as possible knowing the trajectories of the hur-ricane can save many precious lives. So for getting the quick response of the hurricane we used PCA.

1. B. I. Miller, "Characteristics of hurricanes: Analyses and calculations made from measurements by aircraft result in a fairly complete description," Science, vol. 157, no. 3795, pp. 1389{1399, 1967.

2. dataset: https://www.nhc.noaa.gov/

3. S. Alemany, J. Beltran, A. Perez, and S. Ganzfried, “Predicting hurricane trajectories using a recurrentneural network,”Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 02 2018.