Neural Networks for River Flow Prediction

TLDR

River flow hydrographs vary widely due to natural phenomena, and analytic power models often fail to capture this complexity because of simplifying assumptions. The study demonstrates that a neural network can function as an adaptive model synthesizer and predictor for river flow. Using the cascade‑correlation algorithm, the authors selected network architecture and training, applied the model to the Huron River at Dexter, and compared its predictive accuracy and convenience to the standard analytic power model. Preliminary results show the cascade‑correlation networks adapt their complexity to flow history and outperform the power model in accuracy, indicating encouraging performance.

Abstract

The surface‐water hydrographs of rivers exhibit large variations due to many natural phenomena. One of the most commonly used approaches for interpolating and extending streamflow records is to fit observed data with an analytic power model. However, such analytic models may not adequately represent the flow process, because they are based on many simplifying assumptions about the natural phenomena that influence the river flow. This paper demonstrates how a neural network can be used as an adaptive model synthesizer as well as a predictor. Issues such as selecting an appropriate neural network architecture and a correct training algorithm as well as presenting data to neural networks are addressed using a constructive algorithm called the cascade‐correlation algorithm. The neural‐network approach is applied to the flow prediction of the Huron River at the Dexter sampling station, near Ann Arbor, Mich. Empirical comparisons are performed between the predictive capability of the neural network models and the most commonly used analytic nonlinear power model in terms of accuracy and convenience of use. Our preliminary results are quite encouraging. An analysis performed on the structure of the networks developed by the cascade‐correlation algorithm shows that the neural networks are capable of adapting their complexity to match changes in the flow history and that the models developed by the neural‐network approach are more complex than the power model.