Prediction and early estimation of earthquake hazards have always been a subject of research. Indeed, the ability to promptly understand the energy released by a given earthquake event is of utmost importance for rapidly estimating the extent of damage to property and people. Estimating the Magnitude of an earthquake event, and thus the energy released by it, is, however, a slow process, requiring knowledge of the location of the epicenter and, therefore, necessitating the analysis of measurements from several seismic stations. The goal of this work has, hence, been to develop a model that succeeds in providing a coarse estimate, through the use of Artificial Neural Networks, of the Magnitude of a seismic event from the measurements of a single station, with the aim then of refining the estimate in a network of stations. The focus was directed toward estimating the classification uncertainty of the results based on the input measurements' uncertainty to assess the results' reliability.