Effects of Unsaturated Zone on Ground-Water Mounding

The artificial neural networks (ANNs) that try to mimic the functioning of the human brain are a powerful tool for input-output mapping. The setting up of a stage-discharge relation is an important part of the processing of streamflow data. Three-layer feedforward ANNs have been used to model river-rating curves. The results show that the ANN approach is much superior as compared to the conventional curve-fitting approach. The ANN is also able to model a loop-rating curve (hysteresis effect) very well.