A Neural Network for Damaging Wind Prediction

A neural network is developed to diagnose which circulations detected by the National Severe Storms Laboratory's (NSSL) Mesocyclone Detection Algorithm (MDA) yield damaging wind. In particular, 23 variables characterizing the circulations are selected to be used as the input nodes of a feed-forward, supervised neural network. The outputs of the network represent the existence/nonexistence of damaging wind, based on ground observations. A set of fourteen scalar, non-probabilistic measures, and a set of two multi-dimensional, probabilistic measures are employed to assess the performance of the network. The former set includes measures of accuracy, association, discrimination, skill, and the latter consists of reliability and re nement diagrams. Two classi cation schemes are also examined. It is found that a neural network with 2 hidden nodes outperforms a neural network with no hidden nodes when performance is gauged with any of the fourteen scalar measures, except for a measure of discrimination where the results are opposite. The two classi cation schemes perform comparably to one another. As for the performance of the network in terms of reliability diagrams, it is shown that the process by which the outputs are converted to probabilities allows for the forecasts to be completely reliable. Re nement diagrams complete the representation of the calibration-re nement factorization of the joint distribution of forecasts and observations. 2