Detect the Thunderstorms from depends on Weather on its limited spatial and temporal extension either dynamically and physically. This proposed method should give the accurate prediction. Using the Clustering and Wavelet Transform from to successfully predict the thunderstorms resulting with high accuracy. We have to detect the thunderstorms for the forecasting of this service weather feature in advance to reduce the damages. Thunderstorms is very interruption associated with heavy rains, lightning, thunders, thick clouds and gusty surface winds. Actually thunderstorms have spatial area for a few kilometers with a life span less than an hour. Thunderstorm and lightning is a sudden electrical expulsion manifested by a blaze of lightening with a muffled sound. It is one of the most spectacular mesoscale weather phenomena in the atmosphere. Thunderstorm produce lightening, this kills more people every year than tornadoes, and prediction of thunderstorms is the most complicated task in weather forecasting, due to its limited spatial and temporal extension either dynamically or physically. Various researches are been carried on for fore casting of this severe to reduce damage. Many of the researchers proposed various methodologies like STP model, MOM model, CG model, LM model, QKP model, DBD model and so on for the detection, but neither of them could provide an accurate prediction .The proposed system is to gather the satellite images obtained from dataset in order to predict whether the cloud images produces thunderstorms or not.