Earthquake forecast by imbalance machine learning using geophysical predictors

Main Article Content

Tengiz Kiria
Tamaz Chelidze
George Melikadze
Tamar Jimsheladze
Gennady Kobzev


In the present paper we consider the earthquake forecast as a binary problem of machine learning on the imbalanced data base applied to five regions of Georgia. For the training we used geophysical data base collected in 2017-2021, namely, variations of statistical characteristics of geomagnetic field components, seismic activity, water level in deep boreholes and tides. In this version a new predictor – the weighted seismic activity for previous 5 days - – is added compared to the predictors’ list used in previous papers. Besides, the length of the used database is increased 3 times compared to the earlier results. As in the database the earthquakes of M > 3.5 are rare, the number of negative cases is large (there are many days without EQs of M > 3.5), meaning that there is a strong imbalance between positive and negative cases of the order of 1:20; we apply the specific methodology Matthews’ correlation coefficient (MCC) and F1 score to avoid the strong imbalance effect.

Article Details

How to Cite
Kiria, T., Chelidze, T. ., Melikadze, G. ., Jimsheladze, T. and Kobzev, G. (2023) “Earthquake forecast by imbalance machine learning using geophysical predictors ”, Annals of Geophysics, 66(6), p. SE636. doi: 10.4401/ag-8946.
Special Issue: Developments in Earthquake Precursors Studies