Meteorological prediction is one of the most important and challenging task in the modern world．In general，climate is highly non －linear and complicated phenomena，which require advanced method and computer modeling for their accurate prediction． This paper provides a survey of available literature of some methodologies employed by different researchers for the weather forecast based on the methods of data mining at home and abroad． It briefly introduced the concepts and traits of some data mining methods in atmospheric science，separately discussed the basic principles of these data mining methods used in weather forecasting，including the advantages and disadvantages． Finally，the author points out some existing difficulties of data mining methods used in weather forecasting ，and puts forward key points of future research and current trends of the research．