A NEAREST-NEIGHBOR LINEAR PERTURBATION MODEL FOR RIVER FLOW FORECASTING

The non-parametric nearest neighbour method (NNM) for river flow forec asting is explored and developed further as the nearest neighbour line ar perturbation model (NNLPM), which combines the nearest neighbour co ncept with the concept of perturbations from a mean value, as used in the linear perturbation model (LPM). The NNLPM model is tested on six catchments and its results are compared with those of the simple linea r model (SLM) and the linear perturbation model (LPM). The results ind icate that the NNLPM is a more reliable indicator of the discharge for ecast than either the SLM or the LPM in the case of non-seasonal catch ments.