Rainfall Simulation using ANN based Multilayer Perceptron (MLP) and Multiple Linear Regression (MLR) Technique for Bhopal, Madhya Pradesh

Rainfall forecasting represents a tremendously significant matter in field of hydrology. In this study, was undertaken to develop and evaluate the applicability of Multilayer Perceptron (MLP) and Multi Linear Regression (MLR) techniques. The performance of the developed models, on the basis of training and testing, was judged on the basis of four statistical measures such as Root Mean Squared Error (MSE), Coefficient of Efficiency (CE), Correlation Coefficient (r) and Coefficient of Determination(R2) during monsoon period (June to September) for Bhopal, Madhya Pradesh, India. The daily data of minimum temperature, maximum temperature, wind speed and relative humidity were used for rainfall prediction. The appropriate parameter combination of input variables for MLP was used to predict rainfall. The Neuro Solution 5.0 software and Microsoft Excel were used in analysis and the performance evaluation of developed models, respectively. The input pairs in the training data set were applied to the network of a selected architecture and training was performed using back propagation algorithm for MLP models was designed with Gaussian membership function, Takagi- Sugeno- Kang fuzzy model, hyperbolic tangent activation function and Delta-Bar-Delta learning algorithm. Ten MLP models and MLR were selected based on the performance evaluation indices during testing period. MLP models were found to be much closer to the observed values of rainfall as compared to MLR.