Using Lightning Mapping Array data to predict the onset of cloud to ground lightning

We are developing a multi-sensor application that uses iso-therm levels from the Rapid Update Cycle (RUC2) model, radar reflectivity data, Lightning Mapping Array (LMA) data and cloud-to-ground lightning data from the National Lightning Detection Network (NLDN) to predict the onset of cloud-to-ground lightning. The application uses a radial basis function (RBF) to form a relation between past observed reflectivity at various isotherm levels, and in-cloud lightning activity at those levels to current cloud-to-ground lightning activity. The RBF relationship matrix is constantly updated in real-time, and used to predict the onset of cloud-to-ground activity in the future based on current observations of radar reflectivity and LMA data at various isotherm levels. In this paper, we describe the performance and feasibility of such a prediction algorithm. We also explore whether such an algorithm can be trained offline on archived data, instead of actually doing its learning in real time.