Meteorological Insights: Machine Learning in Rainfall Forecasting

Abstract Life would be much easier if we could control the weather. Until then, we will have to settle for trying to predict weather but weather prediction is very unpredictable as even a small change in the surface and atmospheric properties can heavily impact the weather. General weather forecasts, as we all know, are not all that accurate as they attempt to predict the weather conditions of large areas for a large period of time as the tools or mediums used to predict these weather conditions are not accurate enough. To solve the less accurate weather prediction problem, this research work focuses on preparing a algorithm for precipitation forecasting with the parameters such as Temperature, Wind Speed, Wind Direction, Sea level, and Humidity which are the factors that impact the outcome at the particular spot of interest. Here hyper-accurate forecasts including hour-by-hour precipitation prediction with customizable information using supervised machine learning algorithms, Long Short Term Memory (LSTM), Gated Recurrent Units (GRU), and Linear Regression (LR) and feeding historical weather data from the past 40 years have been utilized. The performance of these algorithms is assessed by comparing their results with each other to find the best algorithm suited for this. The test results show that the Recurrent Neural Network (RNN) algorithms excel the linear regression algorithm in accuracy and indicate that RNN algorithms can be an effective way for weather forecasting.