Comparison of short-term rainfall prediction models for real-time flood forecasting

This study compares the accuracy of the short-term rainfall forecasts obtained with time-series analysis techniques, using past rainfall depths as the only input information. The techniques proposed here are linear stochastic auto-regressive moving-average (ARMA) models, artificial neural networks (ANN) and the non-parametric nearest-neighbours method. The rainfall forecasts obtained using the considered methods are then routed through a lumped, conceptual, rainfall-runoff model, thus implementing a coupled rainfall-runoff forecasting procedure for a case study on the Apennines mountains, Italy. The study analyzes and compares the relative advantages and limitations of each time-series analysis technique, used for issuing rainfall forecasts for lead-times varying from 1 to 6 h. The results also indicate how the considered time-series analysis techniques, and especially those based on the use of ANN, provide a significant improvement in the flood forecasting accuracy in comparison to the use of simple rainfall prediction approaches of heuristic type, which are often applied in hydrological practice.