Hari Prasad Chandika1, Eswar Maddi2, Sony Kattepogu3, Venkata Siva Reddy Kandula4, Purna Kommalapati5 1 Assistant Professor, Department of CSE, Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, Andhra Pradesh | Email: hari.chandika@gmail.com 2 UG Student, Department of CSE, Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, Andhra Pradesh | Email: 2002eswar@gmail.com 3 UG Student, Department of CSE, Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, Andhra Pradesh | Email: sonykattepogu3@gmail.com 4 UG Student, Department of CSE, Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, Andhra Pradesh | Email: kandulasiva369@gmail.com 5 UG Student, Department of CSE, Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, Andhra Pradesh | Email: kommalapatipurna@gmail.com
Abstract
Accurate rainfall prediction is essential for agriculture, hydrology, and disaster management. This research evaluates Multiple Linear Regression (MLR), Gradient Boosting (GB), Extreme Gradient Boosting (XGB), and a Voting Regressor ensemble method using climate data from NASA Power spanning 1982โ2023. Performance metrics such as Mean Squared Error (MSE) and explained variance validate the predictive capabilities of these models. Results indicate that ensemble techniques outperform traditional regression approaches, highlighting their ability to capture nonlinear relationships for improved forecasting accuracy.
Hari Prasad Chandika, Eswar Maddi, Sony Kattepogu, Venkata Siva Reddy Kandula, Purna Kommalapati, “An Offline Rainfall Prediction Using MLR and Ensemble Learning,” International Journal of Engineering and Techniques, Volume 10, Issue 2, March 2024. ISSN 2395-1303
Post Comment