Prediction of daily and monthly rainfall using a backpropagation neural network

ABSTRACT In this study, the main goal is to develop a model using artificial intelligence (AI) based on the artificial neural network (ANN) for the prediction of daily and monthly rainfall. The authors compare the prediction accuracy of between daily and monthly rainfall, using meteorological parameters as input information (temperature, dew point, humidity, pressure, visibility, and wind speed). Validation of the developed model is achieved using various quantitative evaluation criteria such as correlation coefficient (R), Root-Mean-Square Error (RMSE), Mean Absolute Error (MAE), which are respectively 0.8063, 0.2487, and 0.0932 for the daily rainfall, and 0.8012, 0.0731 and 0.0578 for monthly rainfall. A comparison is then performed, which shows a higher prediction accuracy of monthly than daily rainfall. These reliable results could help in constructing a soft computing tool to predict accurately and quickly the daily and monthly rainfall.