Thunderstorm tracking system using neural networks and measured electric fields from few field mills

The paper presents a novel system to asses quickly the direction of thunderstorm by using a few field mills on the ground. As opposed to traditional methods using expensive radar systems to detect thundercloud movement, the presented method simply uses the electric waveforms detected by the field mills and, by using a neural network of suitable complexity, can determine the thundercloud´s direction with reasonable accuracy. The neural system is trained with data obtained from the simulation of thundercloud dynamics using parameters observed through experiments. Through extensive testing, it is found that the presented system can reasonably track the direction of the thunderstorm as it propagates while dynamically changing its parameters, and, thus, offers the possibility of creating a practical system. Two types of neural networks are developed and their efficiencies compared.