Seismic phase picking and magnitude estimation are fundamental aspects of earthquake monitoring and seismic event analysis. Accurate phase picking allows for precise characterization of seismic wave arrivals, contributing to a better understanding of earthquake events. Likewise, accurate magnitude estimation provides crucial information about an earthquake's size and potential impact. Together, these components enhance our ability to monitor seismic activity effectively. In this study, we explore the application of deep-learning techniques for earthquake detection and magnitude estimation using continuous seismic recordings. Our approach introduces DynaPicker, which leverages dynamic convolutional neural networks to detect seismic body-wave phases in continuous seismic data. We demonstrate the effectiveness of DynaPicker using various open-source seismic datasets, including both window-format and continuous recordings. We evaluate its performance in seismic phase identification and arrival-time picking, as well as its robustness in classifying seismic phases using low-magnitude seismic data in the presence of noise. Furthermore, we integrate the phase arrival-time information into a previously published deep-learning model for magnitude estimation. We apply this workflow to continuous recordings of aftershock sequences following the Turkey earthquake. The results of this case study showcase the reliability of our approach in earthquake detection, phase picking, and magnitude estimation, contributing valuable insights to seismic event analysis.

Seismic phase picking, which plays an essential role in earthquake location identification and body-wave travel time tomography, is often performed manually. In order to achieve adequately automated seismic phase picking, many conventional approaches have been studied over the past few decades. Common algorithms developed for seismic phase picking include short-time average/long-time average (STA/LTA)

The past decades have witnessed a sharp increase in the number of available seismic data owing to the advancement of seismic equipment and the expansion of seismic monitoring networks. This has increased the demand for a robust seismic phase picking method to deal with large volumes of seismic data. Deep learning has the merit of facilitating the processing of large numbers of data and extracting their features which makes it successful in diverse areas, especially in image processing

Most deep-learning-based seismic phase classification model architectures largely rely on convolutional neural networks (CNNs). A CNN is capable of extracting meaningful features from the input data, which enables the neural network to achieve a good performance. However, most of the prevalent CNN-based models perform inference using static convolution kernels, which may limit their representation power, efficiency, and ability for interpretation. To cope with this challenge, dynamic convolution

Schematic diagram for the proposed dynamic convolution decomposition (DCD)-based model. The model architecture represented on the left side includes a convolutional layer, 1D-DCD layers, and the classifier. The 1D-DCD block displayed on the right side is the backbone of the 1D-DCD layer, which is adapted from the work of

In this work, we pioneer a novel deep-learning-based solution, termed “DynaPicker”, for seismic body-wave phase classification. Furthermore, the phase classifier trained on the short-window data is used to estimate the arrival times of the P-wave and S-wave on the continuous waveform on a long time scale. In DynaPicker, the 1D dynamic convolution decomposition (DCD) adapted from the work of

In order to complete seismic body-wave phase classification and phase onset time picking, the main steps in this study are included as follows. First, the impact of different input data lengths on the performance of seismic phase detection and arrival-time picking are studied on the subset of the STanford EArthquake Dataset (STEAD)

The main contributions of this case study are summarized as follows:

This case study first introduces a deep-learning-based seismic phase identification solution, called “DynaPicker”, which is capable of reliably detecting P- and S-waves of even very small earthquakes, e.g., the local magnitude of the SCEDC dataset ranges from

The results tested on the data of varying lengths indicate that DynaPicker is adaptive to different lengths of input data for seismic phase identification. Moreover, it is proved that DynaPicker is robust in classifying seismic phases even when the seismic data are polluted by noise.

The testing data and the training data used for seismic phase identification and phase picking have no overlap, which proves that DynaPicker is capable of generalizing entire waveforms and metadata archives from different regions.

The CREIME model

In this study, we develop a 1D-DCD-based seismic phase classifier to handle seismic time series data. Our model takes a window of the normalized three-channel seismic waveform as input and predicts its label as P-phase, S-phase, or noise. Then, the pre-trained model is employed to automatically pick the arrival time on the continuous seismic data. Figure

Dynamic convolution achieves a significant performance improvement over convolutional neural networks (CNNs) by adaptively aggregating

However, the vanilla dynamic convolution suffers from two main limitations: firstly, the use of

To address the aforementioned issues,

As presented in Fig.

It is worth noting that the model introduced in this study can be easily adapted to address inputs with different window sizes by simultaneously adjusting the sizes of the first layer and the dynamic classifier layer, respectively. With the goal of verifying the model robustness, the impact of different length data on seismic phase identification is investigated in the following section. The pre-trained model is extensively applied to pick arrival time on continuous data. The process of the arrival-time picking using different window sizes when feeding the same continuous seismic waveform is schematically visualized in Fig.

Visualization of arrival-time picking using DynaPicker for a given normalized seismic waveform. Here, panel

Pipeline of arrival-time picking for continuous seismic waveforms given the pre-trained classifier.

To achieve seismic phase picking, the following steps are included, where the main steps are the same as in GPD

First, each waveform is filtered using the bandpass filter. For instance, the data from the STEAD dataset are filtered within the frequency range 2–20

Then, the waveform is sampled at 100

Afterwards, the data of filtered are divided into several windows. Each window contains a 4 s three-component seismogram (400 samples since the sampling rate is 100

Then, the pre-trained classifier is utilized to predict three sequences of probabilities for each window associated with P-phase, S-phase, and noise, respectively. Following the work of

It is important to mention that the pre-trained versions of GPD and CapsPhase have the softmax function

Finally, the arrival-time detection is declared using the following equation:

In this work, the dataset provided by Southern California Earthquake Data Center (SCEDC)

To achieve seismic phase identification, DynaPicker takes a window of three-channel waveform seismogram data as input, and then for each input, the model predicts the probabilities corresponding to each class (P-wave, S-wave, or noise). This model has three output labels: zero for the P-wave window, one for the S-wave window, and two for the noise window.

In order to further evaluate the model performance in phase arrival-time picking pre-trained on the SCEDC dataset

In this article, noise labels are not treated differently from phase labels, and thus classifying a noise window correctly has the same weight as confirming a phase window. The seismic phase detector can be viewed as a three-class classifier that decides whether a given time window contains a seismic phase (P or S) or only noise. Here, the “noise” windows do not contain P- or S-phases. We can evaluate a deep-learning model by processing labeled testing data where the true output is known. The accuracy defined below is a simple measure of a classifier’s performance:

To evaluate the detector’s effectiveness, a confusion matrix

The F1-score is computed from the harmonic mean of precision and recall for each class:

In this study, for dynamic convolution decomposition units, all the weight and filter matrices are initialized with a normal initializer and bias vectors set to zeros. For optimization, we use the ADAM

Here, we investigate the impact of different input data lengths on the performance of seismic phase detection and arrival-time picking using the STEAD dataset. The details of arrival-time picking using a pre-trained phase classifier can be found in the following subsections and the Methodology section.

To this end, we select 58 018 earthquake waveforms from the STEAD dataset

Then, each dataset is split into a training dataset (90

The confusion matrices corresponding to the input data with different duration are shown in Fig.

Confusion matrices for seismic phase classification given different input data lengths:

In the end, the testing results indicate that our model is adaptive to different lengths of input data. At the same time, our model achieves a compatible performance in seismic phase picking even with low-volume training data.

In this part, the pre-trained DynaPicker on the seismic data with different time duration is further evaluated on continuous seismic data. Moreover, the model is compared with EPick

Body-wave arrival-time evaluation using different window lengths on the STEAD dataset.

As discussed in the previous subsections, the proposed model, DynaPicker, can be adapted to the data with different lengths and achieves compatible performance.

Here, DynaPicker is further retrained and tested on the SCEDC dataset

For further information regarding the retraining of CapsPhase and GPD, and the alterations made to DynaPicker, please refer to the Discussion section.

. Then, we compared our model with CapsPhaseDifferent evaluation metrics, such as the Precision, Recall, and F1-score for DynaPicker, CapsPhase

Results of evaluation metrics on the test dataset

The best-saved model of CapsPhase is directly used here without retraining and, unlike the original CapsPhase

Finally, in order to investigate the model performance when facing more noisy data, the same subset selected from the STEAD dataset used in 1D-ResNet

Testing results of different noise levels for phase identification on the STEAD dataset.

The best-saved model of CapsPhase is directly used here without retraining and unlike the original CapsPhase

We next demonstrate the applicability of our model to pick the seismic phase arrival time for continuous seismic data in the time domain. The main parameters related to phase arrival-time picking are studied in the following section. In this work, DynaPicker is implemented for seismic phase identification given short-window seismic waveforms same as GPD and CapsPhase. Hence, DynaPicker is first compared with two window-based methods including GPD and CapsPhase on both the STEAD dataset and the INSTANCE dataset. Second, we compare DynaPicker with one of the state-of-the-art sample-based seismic phase pickers, EQTransformer

Body-wave arrival-time evaluation using different methods on STEAD dataset including

As presented in GPD

Table

As summarized in Table

Body-wave arrival-time evaluation using different methods on INSTANCE dataset including

The Iquique dataset comprises locally recorded seismic arrivals throughout northern Chile and is used in several previous studies

First, the confusion matrices for P- and S-phase arrival picking results of the experiment using DynaPicker and EQTransformer are shown in Fig.

Visualizations of the testing result on the Iquique dataset. In

Two examples from the Iquique dataset using EQTransformer and DynaPicker are displayed in Fig.

Finally, the absolute error between deep-learning-based model-predicted picks (e.g., EQTransformer and DynaPicker) and manual picks that are below 0.5 s is taken into account. For both P- and S-waves, EQTransformer performs slightly better than DynaPicker in terms of both the root mean square error (RMSE) and the mean absolute error (MAE). Here, the MAE and RMSE of both P- and S-waves using EQTransformer are MAE(P)

In this subsection, we further test the performance of DynaPicker in P-wave onset detection using the published CREIME model

A visualization for combining DynaPicker and CREIME on a seismic recording. DynaPicker uses three-component waveforms to output probabilities corresponding to P- and S-arrivals. The waveform windows with a P-pick probability higher than 0.7 are fed to the CREIME model for magnitude estimation. The red circles represent CREIME predictions while the green squares represent catalog magnitude. A CREIME prediction of less than

Two example earthquakes from the recent Turkey earthquake series and how they were detected using DynaPicker. Green stations correspond to a successful detection, and dotted red ones to an unsuccessful detection. The earthquake epicenter is marked with a star, together with a

We begin by feeding the aftershock waveform of the 2023 Turkey earthquake data into DynaPicker to obtain the P-phase probabilities for each sample. We then use both the waveform windows for which the P-phase probability exceeds 0.7 as input for the CREIME model to estimate the magnitude of the aftershocks. Finally, a seismological expert cross validates the estimated magnitude with the Turkey earthquake catalog (see Table

We also performed retraining on all the models, including DynaPicker, GPD, and CapsPhase, using the SCEDC dataset and applying the early stopping technique, the same as GPD

In Table

This study first introduces a novel seismic phase classifier based on dynamic CNN, which is subsequently integrated into a deep-learning model for magnitude estimation. The classifier consists of a conventional convolution layer and multiple dynamic convolution decomposition layers. To train the proposed seismic phase classifier, we use seismic data collected by the Southern California Seismic Network. The classifier exhibits promising results during testing with earthquake waveforms recorded globally, demonstrating its good generalization ability. Extensive experiments demonstrate that this model yields a superior performance over several baseline methods on phase identification and phase picking. The results from our work contribute to the existing body of literature on supervised deep-learning-based methods for seismic phase classification and demonstrate that with appropriate considerations regarding overfitting and generalization, such methods can improve seismological processing workflows, not just for large catalogs, but also for varying datasets. Moreover, the proposed model is further validated for the monitoring task of the 2023 Turkey earthquake aftershocks.

In this part, the impact of different temperatures in the softmax function (see Eq.

In this part, the impact of different temperatures in the softmax function used on the model performance of phase arrival-time picking for the continuous seismic wave is investigated, as summarized in Table

This part studies the effect of different shift numbers (

Distribution of

Body-wave arrival-time evaluation using different temperatures on the STEAD dataset.

Body-wave arrival-time evaluation using different shift numbers on the STEAD dataset.

Statistical results of magnitude estimation. Mag (MLv) and MagAv (MLv) are the individual magnitudes of each station and the magnitude average values from all stations, respectively, according to the KOERI-RETMC catalog

The seismic dataset of the Southern California Earthquake Data Center used in this study can be accessed at

WL: conceptualization, methodology, software, writing – original draft, writing – review and editing. MC: writing – review and editing, visualization and analysis. JK: writing – review and editing, visualization. CQC: data analysis and validation. GR: writing – review and editing. NS: conceptualization, methodology, writing – review and editing

The contact author has declared that none of the authors has any competing interests.

Publisher’s note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors.

This work is supported by the “KI-Nachwuchswissenschaftlerinnen” – grant SAI 01IS20059 by the Bundesministerium für Bildung und Forschung – BMBF. Calculations were performed at the Frankfurt Institute for Advanced Studies GPU cluster, funded by BMBF for the project Seismologie und Artifizielle Intelligenz (SAI). We thank the authors of Seisbench

This research has been supported by the Bundesministerium für Bildung und Forschung (grant no. SAI 01IS20059).This open-access publication was funded by the Goethe University Frankfurt.

This paper was edited by Ulrike Werban and reviewed by two anonymous referees.