The aim of this research is to deliver climatic insights to clients from various industries, like agriculturists, scholars, and others, so that they may grasp the motive of changes in the climatic and atmospheric features like precipitation, humidity and temperature. One of the most essential areas of meteorological science is estimating precipitation. A combination of factual processes and ML approaches can be utilized to forecast and evaluate meteorological data, including precipitation. These experiment can incorporate daily observations. In explained studies the accuracy of prediction model testing is checked through ground truth validation. These experiment also reveals that ARIMA and Neural Network work well for forecasting meteorological parameters and have the greatest performance when compared to other machine learning techniques for projecting downpour.