Investigation of GPS-TEC measurements using ANN method indicating seismo-ionospheric anomalies around the time of the Chile (Mw = 8.2) earthquake of 01 April 2014

• In Chile a powerful earthquake of Mw = 8.2 took place on April 01, 2014.
• Paper presents an application of ANN method to detect the unusual variations of TEC.
• The results indicate that the ANN is a robust predictor method for TEC time-series.

In 94 km NW of Iquique in Chile (19.610°S, 70.776°W) a powerful earthquake of Mw = 8.2 took place at 23:46:47 UTC (20:46:47 LT) on April 01, 2014. Using GPS-TEC (Total Electron Content) measurements, potential unusual variations around the time and location of the Chile earthquake have been detected based on the median and Artificial Neural Network (ANN) methods. The indices Dst, Kp, Ap and F10.7 were used to distinguish pre-earthquake anomalies from the other anomalies related to the solar-geomagnetic activities. Using the median method, striking anomalies in time series of TEC data are observed 4 days before the earthquake at 14:00 and 16:00 UTC. The ANN method detected a number of anomalies, 4 (02:00 and 16:00 UTC) and 13 (24:00 UTC) days preceding the earthquake. The results indicate that the ANN method due to its capability of non linear learning is quite promising and deserves serious attention as a robust predictor tool for seismo-ionospheric anomalies detection.