Decision Tree, Bagging and Random Forest methods detect TEC seismo-ionospheric anomalies around the time of the Chile, (Mw = 8.8) earthquake of 27 February 2010. Issue 12 (15th June 2016)

• Record Type: Journal Article
• Authors: Akhoondzadeh, Mehdi
• Is Part Of: Advances in space research. Volume 57:Issue 12(2016)
• Page Start: 2464
• Page End: 2469
• Publication Date: 2016-06-15
• Subjects: TEC -- Anomaly detection -- Decision Tree -- Bagging -- Random Forest; Space sciences -- Periodicals; Astronautics -- Periodicals; Geophysics -- Periodicals; 500.505
• DOI: 10.1016/j.asr.2016.03.035
• Languages: English
• ISSNs: 0273-1177

Abstract

Highlights: In Chile a powerful earthquake of Mw = 8.8 took place on February 27, 2010. This paper presents an application of ensemble methods to detect the TEC anomalies. Decision Tree, Bagging and Random Forest are proposed in the field of precursors. The proposed methods deserve serious attention as new predictor tools. Abstract: In this paper for the first time ensemble methods including Decision Tree, Bagging and Random Forest have been proposed in the field of earthquake precursors to detect GPS-TEC (Total Electron Content) seismo-ionospheric anomalies around the time and location of Chile earthquake of 27 February 2010. All of the implemented ensemble methods detected a striking anomaly in time series of TEC data, 1 day after the earthquake at 14:00 UTC. The results indicate that the proposed methods due to their performance, speed and simplicity are quite promising and deserve serious attention as a new predictor tools for seismo-ionospheric anomalies detection.