Abnormal Weather Prediction: A New Method Combining Rough Set, BP Neural Network and Temporal Association Rules

摘要

Abnormal weather alerts and advisories play a significant role in the process of protecting life and property which have been a major part of modern weather forecasting. In this paper a new model was proposed that called RSBP-TAR combined Rough Set with Back propagation Propagation Neural Network to mine some Temporal Association Rules from the past meteorological satellite data, from which we can develop the accuracy of the lowest and highest weather alerts and advisories through the time lag of two cities's temperature change.