Magnetic Control of the Earthquakes

Бучаченко, А. Л.

doi:10.4236/ojer.2021.104009

Cited by 5 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Anomalies in hydraulic [Wang and Manga, 2010] and geomagnetic data [Balasis et al, 2011;Zotov et al, 2013;Buchachenko, 2021] as the phenomena observed in the precursor manifestation area R. Here we choose the radius of manifestation area (interaction length) R = 200 km for hydraulic precursors of EQs of M > 3.5 for a given well.…”

Section: The Network Of Observations Preparation Of Data Bases and Me...mentioning

confidence: 99%

Earthquake forecast by imbalance machine learning using geophysical predictors

Kiria,

Chelidze,

Melikadze

et al. 2023

Annals of Geophysics

View full text Add to dashboard Cite

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.

show abstract

Section: The Network Of Observations Preparation Of Data Bases and Me...mentioning

confidence: 99%

Earthquake forecast by imbalance machine learning using geophysical predictors

Kiria,

Chelidze,

Melikadze

et al. 2023

Annals of Geophysics

View full text Add to dashboard Cite

show abstract

“…The geomagnetic field at DGO is sensitive to remote earthquakes [10] [11]. There are two magnetic anomalies mainly in X and Y components, approximately around 09.01.22 (relatively weak) and 14.01.2022 (strong).…”

Section: Geomagnetic Field Registered At the Dusheti Geophysicalmentioning

confidence: 99%

Geophysical Reactions to Remote 2022 Tonga Eruption and to Türkiye Earthquakes in Georgia (Caucasus): Hydrogeology, Geomagnetics and Seismicity

Chelidze,

Melikadze,

Kobzev

et al. 2023

OJER

View full text Add to dashboard Cite

The paper is devoted to analysis of hydrogeological, geomagnetic and seismic response to the two great remote geophysical events, 2022 Tonga volcano eruption and 2020-2023 Türkiye earthquakes in Georgia (Caucasus). The geophysical observation system in Georgia, namely, water level stations in the network of deep wells, atmospheric pressure and the geomagnetic sensors of the Dusheti Geophysical Observatory (DGO) as well as seismic data in Garni Observatory (Armenia) respond to the Tonga event by anomalies in the time series. These data show that there are two types of respond: infrasound disturbances in atmospheric pressure and seismic waves in the Earth generated by the eruption. After Tonga eruption January 15 at 04:21 UTC three groups of N-shaped waveforms were registered in the water level corresponding to the global propagation characteristics of the N-shaped waveform of infrasound signals on the barograms generated by eruption at the distance ~15,700 km: they were identified as the Lamb wave, a surface wave package running in the atmosphere with a velocity around ~314 m/s. The paper also presents the WL reactions to three strong EQs that occur in Türkiye 2020-2023, namely Elazığ, Van and Türkiye-Syria EQs. WL in Georgian well network reacts to these events by anomalies of different intensity, which points to the high sensitivity of hydrosphere to remote (several hundred km) strong EQs. The intensity and character of WL reactions depend strongly on the local hydrogeological properties of rocks, surrounding the well.

show abstract

“…We are looking for hydraulic (Wang and Manga, 2010) and geomagnetic anomalies (Zotov et al, 2013;Buchachenko, 2021) in the "quasiepicentral" or a precursor interaction area R. We choose the interaction length R = 200 km for hydraulic precursors of EQs of M ≥ 3.5 for a given well. Note that there are different assessments of the EQ precursors' area.…”

Section: Network Devices and Datamentioning

confidence: 99%

Earthquake Forecast as a Machine Learning Problem for Imbalanced Datasets: Example of Georgia, Caucasus

et al. 2022

View full text Add to dashboard Cite

In this article, we considered the problem of M≥3 earthquake (EQ) forecasting (hindcasting) using a machine learning (ML) approach, using experimental (training) time series on monitoring water-level variations in deep wells as well as geomagnetic and tidal time series in Georgia (Caucasus). For such magnitudes’, the number of “seismic” to “aseismic” days in Georgia is approximately 1:5 and the dataset is close to the balanced one. However, the problem of forecast is practically important for stronger events—say, events of M≥3.5—which means that the learning dataset of Georgia became more imbalanced: the ratio of seismic to aseismic days for in Georgia reaches the values of the order of 1:20 and more. In this case, some accepted ML classification measures, such as accuracy leads to wrong predictions due to a large number of true negative cases. As a result, the minority class, here—seismically active periods—is ignored at all. We applied specific measures to avoid the imbalance effect and exclude the overfitting possibility. After regularization (balancing) of the training data, we build the confusion matrix and performed receiver operating classification in order to forecast the next day probability of M≥3.5 earthquake occurrence. We found that the Matthews’ correlation coefficient (MCC) is the measure, which gives good results even if the negative and positive classes are of very different sizes. Application of MCC to observed geophysical data gives a good forecast of the next day M≥3.5 seismic event probability of the order of 0.8. After randomization of EQ dates in the training dataset, the Matthews’ coefficient efficiency decreases to 0.17.

show abstract

Magnetic Control of the Earthquakes

Cited by 5 publications

References 26 publications

Earthquake forecast by imbalance machine learning using geophysical predictors

Earthquake forecast by imbalance machine learning using geophysical predictors

Geophysical Reactions to Remote 2022 Tonga Eruption and to Türkiye Earthquakes in Georgia (Caucasus): Hydrogeology, Geomagnetics and Seismicity

Earthquake Forecast as a Machine Learning Problem for Imbalanced Datasets: Example of Georgia, Caucasus

Contact Info

Product

Resources

About

Magnetic Control of the Earthquakes

Cited by 5 publications

References 26 publications

Earthquake forecast by imbalance machine learning using geophysical predictors

Earthquake forecast by imbalance machine learning using geophysical predictors

Geophysical Reactions to Remote 2022 Tonga Eruption and to T&#252;rkiye Earthquakes in Georgia (Caucasus): Hydrogeology, Geomagnetics and Seismicity

Earthquake Forecast as a Machine Learning Problem for Imbalanced Datasets: Example of Georgia, Caucasus

Contact Info

Product

Resources

About

Geophysical Reactions to Remote 2022 Tonga Eruption and to Türkiye Earthquakes in Georgia (Caucasus): Hydrogeology, Geomagnetics and Seismicity