Rainfall Intensity Prediction System using Machine Learning Techniques

M.Chandan Kumar¹, N.Srujana², P.Aswanth³, T.Dharma⁴
Supervisor: Ms.M.Sowjanya,M.Tech(PhD), Assistant Professor, Dept. of CSE, VIET
¹Department of CSE (AIML), Visakha Institute of Engineering and Technology, Andhra Pradesh, India
2Department of CSE (AIML), Visakha Institute of Engineering and Technology, Andhra Pradesh, India
3Department of CSE (AIML), Visakha Institute of Engineering and Technology, Andhra Pradesh, India
4Department of CSE (AIML), Visakha Institute of Engineering and Technology, Andhra Pradesh, India

Abstract - This study presents the development of amachine learning-based rainfall prediction system using historical meteorological data. Rainfall prediction plays a crucial role in agriculture, water resource management, and disaster prevention. Traditional forecasting methodsoften fail to capture the complex and non-linear relationships between atmospheric parameters, leading to inaccurate predictions. In this project, a dataset containing weather parameters such as temperature, dew point, humidity, sea level pressure, visibility, wind speed,month, and day was used to train machine learning models. Data preprocessing techniques including handling missing values using median imputation, outlier removal using the Interquartile Range (IQR) method, and log transformation for skewness reduction were appliedto improve data quality. Among various machine learning algorithms, Extreme Gradient Boosting (XGBoost) was selected due to its superior performance in handling non linear data and providing high prediction accuracy. Key Words: Machine Learning, Rainfall Prediction,XGBoost, Data Pre-processing, Stream lit, Regression