Forecasting of Weather is a complex and challenging task for a scientist. It is almost complicated due to chaos behavior of climatic data. However, since 1986 neural network based numerical modeling for the same is suggested by the world’s scientific community and shown some extent of success. In this study, a comprehensive review of various contributions from 1997 to 2017. Wherein models of various contribution is studied year wise. As a result, soft-computing i.e., neural network, deep learning technique, data mining such as associative classifier has been found to be successfully applied. Finally, it is concluded that BPN is sufficient enough to resolve this complex problem. It has shown 90% accuracy in modeling. However, obtaining optimum architecture for better performance is a pre-requisite. These evidences are broadly discussed in this review article.
