Search

In this paper, a scalable end-to-end tree boosting system called XGBoost has been applied for predicting the magnitude of an earthquake from the early part of earthquake waveform data. This model uses the features extracted from the early P wave phase of the records as an input. The model's effectiveness has been verified by using data on earthquakes occurring in the Eurasian plate of Japan Islands from 1996 to 2021. Feature engineering has given 29 new features identified from the early P wave phase of the record, which show a high correlation with the magnitude of an earthquake. The comparison of predicted and actual magnitude shows that a trained XGboost model, which uses a single input record for magnitude prediction, gives an average prediction error of 0.004 ± 0.57 for earthquakes in the test dataset. In contrast, the average prediction error of –1.1 ± 0.80 and –0.65 ± 0.69 has been obtained for the magnitude estimated from conventional τc and Pd methods using the same test dataset. It is further seen that the average predicted magnitude of a single earthquake of magnitude 4.5 and 6.1 (MJMA) obtained by using multiple nearfield records using XGBoost model is 4.58 ± 0.33 and 6.32 ± 0.29, which is close to the actual magnitude of the earthquake. The results presented in this paper clearly show that the structured data can be effectively used by complex machine learning or deep learning models to predict earthquake magnitude from single or multiple records. [ABSTRACT FROM AUTHOR]

We report precursory seismic patterns prior to the 2016 Kumamoto earthquakes, as measured by four different methods based on changes in seismicity that can be used for earthquake forecasting: the b-value method, two methods of seismic quiescence evaluation, and an analysis of seismicity density in space and time. The spatial extent of precursory patterns differs from one method to the other and ranges from local scales (typically, asperity size) to regional scales (e.g., 2° × 3° around the source zone). The earthquakes were preceded by periods of pronounced anomalies, which lasted in yearly scales (1.5 years), or longer (>3 years). We demonstrate that a combination of multiple methods detected different signals prior to the Kumamoto earthquakes. This indicates great potential to reduce the hazard at possible future sites of earthquakes relative to long-term seismic hazard assessment. We also found that the seismic quiescence in a regional-scale area, detected by using the two methods of seismic quiescence evaluation, was a common precursor to the 2016 Kumamoto earthquakes and 2015 Off Satsuma Peninsula earthquake. The result allows us to interpret both events as the onset that occurred at a section along the tectonic line from the Okinawa Trough through the Beppu-Shimabara graben. [ABSTRACT FROM AUTHOR]