Learning Networks For Tornado Forecasting: A Bayesian Perspective
Free (open access)
T. B. Trafalis, B. Santosa & M. B. Richman
In this paper, different types of learning networks, such as artificial neural networks (ANNs), Bayesian neural networks (BNNs), support vector machines (SVMs) and Bayesian support vector machines (BSVMs) are applied for tornado forecasting. The last two approaches utilize kernel methods to address nonlinearity of the data in the input space. All methods are applied to forecast when tornadoes occur, using variables based on radar derived velocity data and month number. Computational results indicate that Bayesian methods have a higher skill level compared to ANNs and SVMs for a tornado forecast system. Keywords: artificial neural networks, Bayesian framework, Bayesian neural networks, Bayesian support vector machines, kernel functions, support vector machines. 1 Introduction Detection of tornadoes with ample warning times is a goal of severe weather forecasters. With state-of-the-science weather radar, high speed computing and advanced signal processing algorithms, steady progress is being made on increasing the average lead-time of such warnings. As evidenced in the spring of 2003 in the United States, with a record number of tornadoes and a relatively small number of deaths, an extra minute of lead-time in tornado warnings can translate into a number of lives saved. One of the severe weather detection algorithms, created by the National Severe Storms Laboratory (NSSL) and in use at the Weather Surveillance Radar 1998 Doppler (WSR-88D), is the Mesocyclone Detection Algorithm (MDA). This algorithm uses the outputs of the WSR-88D and is designed to detect storm–scale circulations associated with
artificial neural networks, Bayesian framework, Bayesian neural networks, Bayesian support vector machines, kernel functions, support vector machines.