Detection of Weak Seismo-Electric Signals Upon the Recordings of the Electrotelluric Field by Means of Neuro-Fuzzy Technology

This letter presents the development and application of prediction-based adaptive filters incorporated with neuro-fuzzy technology for the emergence and detection of weak electrotelluric potential anomalies appearing upon recordings of the Earth´s electric field. Electric earthquake precursors (EEPs) are considered to be related with forthcoming seismic events and, in many cases, are hidden in the electrotelluric field background. Their detection can be further complicated by the probable appearance of severe transient fluctuations induced mainly by magnetic storms and/or other physical and anthropogenic types of noise. This application presents two neuro-fuzzy models trained to predict the recorded magnetic and electric fields´ variations, respectively. The overall method aims to reveal and detect EEP signals upon the error signal, defined as the difference between the recorded electric field signal and the electric field signal predicted by the secondary neuro-fuzzy model, while the primary neuro-fuzzy model minimizes the effect of noise of magnetotelluric origin upon the recorded electric field