Neural Network vs. ARMA Modelling: constructing benchmark case studies of river flow prediction

This paper provides forecasting benchmarks for river flow prediction in the form of a numerical comparison between neural networks and ARMA models. Naive predictions are also provided. Benchmarking was based on a three year period of continuous river flow data for two catchments: the Upper River Wye (Central Wales) and the River Ouse (Yorkshire). Two sets of benchmarks have been established: (i) modelling the central year, with the two adjacent years being used for validation purposes; and (ii) modelling the entire three year period, with the relative performance of each individual year being used as a metric. The choice of an appropriate neural network architecture for hydrological forecasting, in terms of hidden layers and nodes, was first investigated. Two simple neural network architectures were selected for more detailed evaluation from which one final design was then chosen for comparison with the ARMA model and naive prediction forecasts. Six global evaluation measures were used to provide ‘goodness-of-fit’ statistics. Alternative evaluation measures were also used to examine specific performance on storm events, such as peak prediction, and time-to-peak. The benchmark results showed that simple neural networks were able to produce similar results to ARMA models given the same data inputs. Finally, a self-organising map was used to split the data series into classes, where each class represents a different type of hydrological event e.g. rising limb, falling limb, etc. Two rising event types were then modelled with a neural network and improved forecasting performance obtained. The results from this data-splitting operation suggest some interesting possibilities for future multi-network modelling explorations, and point to the clear need for current benchmarks against which all such advances can be compared.