Published Paper Details:

Predicting when it will rain is crucial for warning individuals of potential dangers and enabling them to take preventative measures for their own safety. This work aims to employ machine learning algorithms to accurately estimate rainfall, taking into account the substantial effects of little or excessive rainfall on both rural and urban life. Rainfall is a complicated phenomenon that is influenced by a wide range of meteorological, oceanic, and geographical factors, making it challenging to predict. This study makes use of a variety of machine learning algorithms, such as Support Vector Machine (SVM) and Random Forest classifier, as well as data pretreatment techniques, feature selection, model selection, and evaluation. The aim of the project is to develop the most accurate rainfall forecast model feasible by utilizing feature selection and machine learning techniques. While the Random Forest classifier obtained 84% accuracy by using ensemble learning and decision trees, which are excellent at capturing complicated correlations in data, the SVM only reached 83% accuracy by specifying a linear decision boundary, possibly restricting its ability to handle sophisticated data patterns.