Comparative Analysis of Rainfall Prediction Models Using Neural Network and Fuzzy Logic
Afolayan Abimbola Helen1, Ojokoh Bolanle A.2, Falaki Samuel O.3
1Afolayan Abimbola Helen, An Assistant Lecturer and a Ph.D. student, Department of Computer Science, Federal University of Technology, Akure, Nigeria.
2Dr (Mrs) Ojokoh Bolanle A., A Senior Lecturer, Department of Computer Science, Federal University of Technology, Akure, Nigeria.
3Prof. Falaki Samuel O., A Professor of Computer Science in the Department of Computer Science, Afe Babalola University, Ado Ekiti, Nigeria.
Manuscript received on December 16, 2016 . | Revised Manuscript received on December 27, 2016 . | Manuscript published on January 05, 2016 . | PP: 4-7 | Volume-5 Issue-6, January 2016 . | Retrieval Number: D2689095415/2016©BEIESP
Open Access | Ethics and Policies | Cite
©The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Rainfall is a stochastic process, whose upcoming event depends on some precursors from other parameters such as temperature, surface pressure and other atmospheric parameters.Accurate information about rainfall is necessary for the use and management of water resources. Nonetheless, rainfall is one of the most complex and difficult elements in hydrology due to the tremendous range of variation over a wide range of scales both in space and time. Forecasting techniques such as Artificial Neural Network (ANN) and Fuzzy Logic (FL) have been used to study rainfall. This research work is motivated by the need to compare ANN and FL models to know which one is more efficient in predicting rainfall. The rainfall datasets used in this research work were collected from an automatic weather station in Iju, a town in Akure North Local Government Area of Ondo State for the period of four years (2007-2010). The model comparison is based on four criteria; the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), prediction error, and the prediction accuracy. The error measures are comparable for the two models. The analysis of the models accuracy, shows that, overall, the ANN model perform slightly better than the FL model in terms of PE, RMSE, MAE andaccuracy.
Keywords: Forecasting, Fuzzy Logic, Neural Networks, ,Rainfall.