Point Rainfall Prediction using Data Mining Technique

T.R. Sivaramakrishnan ； S. Meganathan

《Research Journal of Applied Sciences, Engineering and Technology》 4卷13期 (2012/07) Pp. 1899-1902

並列摘要

Rainfall prediction is usually done for a region but spot quantitative precipitation forecast is required for individual township, harbours and stations with vital installation. With recent successful attempt for prediction of rainfall at a coastal station in east coast of India, a methodology to predict spot rainfall using association rule mining for an interior station Trichirappalli (10°48' N/78°41' E) of south India has been developed and the results are presented here. The data is filtered using discretization approach based on the best fit ranges and then association mining is performed on dataset using Predictive Apriori algorithm and then the data need be validated using K* classifier approach. The results show that the overall classification accuracy for occurrence and non occurrence of the rainfall on wet and dry days using the data mining technique is satisfactory.

並列關鍵字

Association rule mining ； data mining ； K* algorithm ； predictive apriori algorithm ； rainfall prediction