Indonesian Journal of Electrical Engineering and Computer Science Vol. 22, No. 2, May 2021, pp. 1208~1215 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v22.i2.pp1208-1215  1208 Journal homepage: http://ijeecs.iaescore.com Weather prediction using random forest machine learning model R. Meenal 1 , Prawin Angel Michael 2 , D. Pamela 3 , E. Rajasekaran 4 1, 2 Department of Electrical and Electronics Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India 3 Department of Biomedical Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India 4 Department of Science and Humanities, VSB Engineering College, Karur, India Article Info ABSTRACT Article history: Received Jan 26, 2021 Revised Mar 20, 2021 Accepted Apr 7, 2021 The complex numerical climate models pose a big challenge for scientists in weather predictions, especially for tropical system. This paper is focused on presenting the importance of weather prediction using machine learning (ML) technique. Recently many researchers recommended that the machine learning models can produce sensible weather predictions in spite of having no precise knowledge of atmospheric physics. In this work, global solar radiation (GSR) in MJ/m2/day and wind speed in m/s is predicted for Tamil Nadu, India using a random forest ML model. The random forest ML model is validated with measured wind and solar radiation data collected from IMD, Pune. The prediction results based on the random forest ML model are compared with statistical regression models and SVM ML model. Overall, random forest machine learning model has minimum error values of 0.750 MSE and R2 score of 0.97. Compared to regression models and SVM ML model, the prediction results of random forest ML model are more accurate. Thus, this study neglects the need for an expensive measuring instrument in all potential locations to acquire the solar radiation and wind speed data. Keywords: Artificial intelligence Machine learning Random forest Renewable energy This is an open access article under the CC BY-SA license. Corresponding Author: R. Meenal Department of Electrical and Electronics Engineering Karunya Institute of Technology and Sciences Coimbatore-641114, Tamil Nadu, India Email: meenasekar5@gmail.com 1. INTRODUCTION Weather forecasts are very essential for a safe and efficient management of the power grid. Solar and Wind energy are the main renewable energy sources owing to its simplicity of access and surplus in major parts of the world. Accurate knowledge of solar and wind data is very essential for renewable energy based applications. The solar and wind data is not available in all the locations of the worls because of high cost and difficulties in measurement techniques. Because of the data scarcity, solar radiation and wind speed prediction plays an important role for effective and proper utilization of these renewable energy sources. This study is focused on neglecting the need of expensive measuring instruments to acquire the wind speed and solar radiation data. There are many approaches available in the literature for the prediction of wind speed and radiation including the physical methods, persistence method, statistical methods, spatial correlation methods, artificial intelligence methods, hybrid methods and so on [1]-[5]. Artificial intelligence based methods are widely used for the estimation of wind speed and solar radiation [6]-[10]. The physical models are complex and time consuming. In the climate change models, there are noticeable flaws pertaining to the