Abstract
The National Severe Storms Laboratory's (NSSL) mesocyclone detection algorithm (MDA) is designed to scotch for patterns in Doppler velocity radar data that are associated with rotating updrafts in severe thunderstorms. These storm-scale circulations are typically precursors to tornados and severe weather in thunderstorms, yet not all circulations produce such phenomena.
A neural network has been designed to diagnose which circulations detected by the NSSL MDA yield tornados. The data used both for the training and the testing of the network are obtained from the NSSL MDA. In particular, 23 variables characterizing the circulations are selected to be used as the input nodes of a feed-forward neural network. The output of the network is chosen to be the existence/nonexistence of tornados, based on ground observations. It is shown that the network outperforms the rule-based algorithm existing in the MDA, as well as statistical techniques such as discriminant analysis and logistic regression. Additionally, a measure of confidence is provided in terms of probability functions.
