Cyclones endanger life and cause great financial impact on interior and coastal regions through the destruction of buildings and land. Governments need to have a way of estimating the chance of different regions being impacted by a cyclone. The goal of this paper is to use big data to better predict future cyclone impacts. Large cyclone data sets from the CMA Tropical Cyclone Data Center are used in the analysis. By using big data analysis techniques, long-term patterns in cyclone locations and size can be revealed. The Hausdorff distance is used to determine overall changes in cyclone positions decade by decade. Monte Carlo techniques estimate the probability of a region being impacted by a cyclone any given year. This is done by creating random data sets that mimic long-term patterns in cyclone position and radii. It will be shown that any region can be assigned a probability of cyclone impact purely on large historical data sets.

飓风通过破坏建筑物和土地，危及生命，并对内陆和沿海地区造成巨大的经济影响。政府需要有一种方法来估计不同地区受到旋风影响的机会。本文的目的是利用大数据更好地预测未来的旋风影响。分析中使用了来自CMA热带气旋数据中心的大型气旋数据集。通过使用大数据分析技术，可以揭示旋风分离器位置和大小的长期格局。Hausdorff距离用于确定十年一度的气旋位置的整体变化。蒙特卡洛技术估计任何给定年份某个地区受到旋风影响的可能性。这是通过创建模拟气旋位置和半径的长期模式的随机数据集来完成的。