The effects of detector spacing on traffic forecasting performance using neural networks

An investigation was made as to how short-term traffic forecasting on motor way and other trunk roads is related to the density of detectors. Forecasti ng performances with respect to different detector spaces have been investi gated with both simulated data and real data. Pruning techniques to the inp ut variables used for neural networks were applied to the simulated data. T he real data were collected from the M25 motorway and included flow, speed, and occupancy. With the data used in our study, the forecasting performanc es decrease with the increase of detector spaces. However by taking the ass umed costs of detector infrastructure into account, it may be concluded fro m this study that increasing coverage to a spacing of 500 m gives little ex tra benefit and may actually be counter productive in certain circumstances . It was concluded that, on the basis of current evidence, a detector spaci ng of between 1 and 1.5 km might be optimal.