Sequential GMDH Algorithm and Its Application to River Flow Prediction

A heuristic self-organization method for constructing a nonlinear river flow prediction model from the available data such as river flow and areal mean precipitation is presented. Our algorithm, the improved version of the GMDH proposed by A. G. Ivakhnenko, is useful for the prediction of complex nonlinear systems with a large number of variables and with a small amount of available input-output data. The efficiency and usefulness of the proposed sequential prediction algorithm are shown by the use of a simulation model. This algorithm is applied to the flow prediction of the Karasu River in Japan. Numerical comparisons are performed between the prediction model by "sequential GMDH" and by the elaborate hydrologic methods, and we show that there are improvements in the newly introduced prediction algorithm for real-time computation.