TY - JOUR

T1 - Determining the Arrival Times of Direct P- and S-Waves for Weak Earthquakes Using Machine Learning

AU - Kamashev, A. M.

AU - Duchkov, A. A.

AU - Yaskevich, S. V.

N1 - The study was supported by the Russian Science Foundation (project no. 23-17-00237). Kamashev, A. M. Determining the Arrival Times of Direct P- and S-Waves for Weak Earthquakes Using Machine Learning / A. M. Kamashev, A. A. Duchkov, S. V. Yaskevich // Seismic Instruments. – 2025. – Vol. 61, No. 3. – P. 245-259. – DOI 10.3103/S0747923925700380.

PY - 2025/10/1

Y1 - 2025/10/1

N2 - We suggest an approach to automatic picking of P- and S-wave arrival times when processing data from local seismological-monitoring network. A distinctive feature of this approach is that it does not attempt to train a universal neural network for processing all types of seismological data. Instead, we focus on one specific region at a time, which significantly narrows the requirements for the training dataset size and variability. An important result is the automatic quality-control tool, since it simultaneously ensures the accuracy of the accepted events as well as forms a fairly small dataset of rejected events. This small dataset can be further used for manual processing and additional neural-network training. This approach was tested on real data from two local seismological networks located in different regions. We demonstrate that a small seismological dataset can be used for training the neural network for processing seismological data from a specific region: records from 20–40 local earthquakes. For high-quality data, it is possible to pick the arrival times of P- and S-waves with an error less than 50 ms for 94 and 88% of cases, respectively. For the poor-quality dataset, it was possible to determine the arrival times of P- and S-waves with an error less than 200 ms in 82 and 73% of cases, respectively. The proposed approach makes it possible to accelerate automatic processing by reducing the required size of the training sample; the approach was implemented in stream processing for the considered seismological networks.

AB - We suggest an approach to automatic picking of P- and S-wave arrival times when processing data from local seismological-monitoring network. A distinctive feature of this approach is that it does not attempt to train a universal neural network for processing all types of seismological data. Instead, we focus on one specific region at a time, which significantly narrows the requirements for the training dataset size and variability. An important result is the automatic quality-control tool, since it simultaneously ensures the accuracy of the accepted events as well as forms a fairly small dataset of rejected events. This small dataset can be further used for manual processing and additional neural-network training. This approach was tested on real data from two local seismological networks located in different regions. We demonstrate that a small seismological dataset can be used for training the neural network for processing seismological data from a specific region: records from 20–40 local earthquakes. For high-quality data, it is possible to pick the arrival times of P- and S-waves with an error less than 50 ms for 94 and 88% of cases, respectively. For the poor-quality dataset, it was possible to determine the arrival times of P- and S-waves with an error less than 200 ms in 82 and 73% of cases, respectively. The proposed approach makes it possible to accelerate automatic processing by reducing the required size of the training sample; the approach was implemented in stream processing for the considered seismological networks.

KW - LOCAL EARTHQUAKES

KW - SEISMIC MONITORING

KW - artificial neural networks

KW - WAVE ARRIVAL TIMES

KW - AUTOMATIC PROCESSING

UR - https://www.mendeley.com/catalogue/2fee9f02-5963-337c-8b41-8b797436f8a4/

UR - https://elibrary.ru/item.asp?id=83051560

U2 - 10.3103/s0747923925700380

DO - 10.3103/s0747923925700380

M3 - Article

VL - 61

SP - 245

EP - 259

JO - Seismic instruments

JF - Seismic instruments

SN - 0747-9239

IS - 3

ER -