Rainfall-Runoff Modeling at Daily Scale with Artificial Neural Networks

The artificial neural networks (ANNs) have been applied to various hydrologic problems recently. This research demonstrates a back-propagation (BP) neural networks model and a distributed hydrologic model for rainfall-runoff modeling in the upper area of Huai River, China. Methodologies and techniques of the two models are presented in this paper and a comparison of the simulated results between them is also conducted. The simulated results of the BP model indicate a satisfactory performance in the daily-scale simulation. The conclusions also indicate that the ANN-hydrologic models can be considered as an alternate and practical tool for hydrologic simulations in hydrologic science domain.