Rainfall intensity has a significant impact on urban drainage infrastructures and the precipitation forecast therefore remains essential in urban areas. In this study, a prediction model using Nonlinear Autoregressive Neural Networks (NANN) was proposed to forecast 48-hour-ahead the rainfall intensity. The proposed NANN model, which is based on a precipitation data of five-year time series, was constructed and validated using various parameters such as Coefficient of Determination (R2), Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The results exhibited a high statistical correlation between the outputs of NANN model and the measured data for 48 hour ahead prediction, i.e. R2=0.8998, RMSE=3.2909 and MAE=1.8672. This indicates that the developed model is very promising for precipitation forecasting and could contribute to improve the urban drainage systems.
CITATION STYLE
Le, T. T., Pham, B. T., Ly, H. B., Shirzadi, A., & Le, L. M. (2020). Development of 48-hour precipitation forecasting model using nonlinear autoregressive neural network. In Lecture Notes in Civil Engineering (Vol. 54, pp. 1191–1196). Springer. https://doi.org/10.1007/978-981-15-0802-8_191
Mendeley helps you to discover research relevant for your work.