Prediction of Rainfall using Machine Learning
S.Poornima1, S.Devi2, D.Oviya3, A.Suhana Taj4, G.Tamil Elakkiya5
1S. Poornima*, Department of Information Technology, Coimbatore Institute of Technology, Coimbatore, India.
2S. Devi, Department of Information Technology, Coimbatore Institute of Technology, Coimbatore, India.
3D.Oviya, Department of Information Technology, Coimbatore Institute of Technology, Coimbatore, India.
4A.Suhana Taj, Department of Information Technology, Coimbatore Institute of Technology, Coimbatore, India.
5G.Tamil Elakkiya, Department of Information Technology, Coimbatore Institute of Technology, Coimbatore, India.
Manuscript received on April 30, 2020. | Revised Manuscript received on May 06, 2020. | Manuscript published on May 30, 2020. | PP: 1374-1377 | Volume-9 Issue-1, May 2020. | Retrieval Number: A2242059120/2020©BEIESP | DOI: 10.35940/ijrte.A2242.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Rainfall is one of the major livelihood of this world. Each and every organism in this universe need some of water to order to survive in its own living conditions. As rainfall is the main source of water and its need to agriculture is inevitable, there arises a necessity to analyze the pattern of the rainfall. The main aim of our paper is to predict the rainfall considering various factors like temperature, pressure, cloud cover, wind speed, pollution and precipitation. There are various ideas and new methodologies proposed in order to predict rainfall. But our proposed concept is based on machine learning because of its wide range of development and preferability nowadays. Among the various technologies built in Machine Learning (ML), Feed Forward Neural Network (FFNN) which is the simplest form of Artificial Neural Network (ANN) is preferred because this model learns the complex relationships among the various input parameters and helps to model them easily. Rainfall in our proposed model is predicted using different parameters influencing the rainfall along with their combinations and patterns. The experimental results depicts that the proposed model based on FFNN indicates suitable accuracy.
Keywords: Rainfall Prediction; Feed Forward Neural Network; Humidity, precipitation.
Scope of the Article: Machine Learning