Explore the vast range of titles available.

Signal denoising is one of the most important issues in signal processing, and various techniques have been proposed to address this issue. A combined method involving wavelet decomposition and multiscale principal component analysis (MSPCA) has been proposed and exhibits a strong signal denoising performance. This technique takes advantage of several signals that have similar noises to conduct denoising; however, noises are usually quite different between signals, and wavelet decomposition has limited adaptive decomposition abilities for complex signals. To address this issue, we propose a signal denoising method based on ensemble empirical mode decomposition (EEMD) and MSPCA. The proposed method can conduct MSPCA-based denoising for a single signal compared with the former MSPCA-based denoising methods. The main steps of the proposed denoising method are as follows: First, EEMD is used for adaptive decomposition of a signal, and the variance contribution rate is selected to remove components with high-frequency noises. Subsequently, the Hankel matrix is constructed on each component to obtain a higher order matrix, and the main score and load vectors of the PCA are adopted to denoise the Hankel matrix. Next, the PCA-denoised component is denoised using soft thresholding. Finally, the stacking of PCA- and soft thresholding-denoised components is treated as the final denoised signal. Synthetic tests demonstrate that the EEMD-MSPCA-based method can provide good signal denoising results and is superior to the low-pass filter, wavelet reconstruction, EEMD reconstruction, Hankel–SVD, EEMD-Hankel–SVD, and wavelet-MSPCA-based denoising methods. Moreover, the proposed method in combination with the AIC picking method shows good prospects for processing microseismic waves.

Seismic wave arrival time measurements form the basis for numerous downstream applications. State‐of‐the‐art approaches for phase picking use deep neural networks to annotate seismograms at each station independently, yet human experts annotate seismic data by examining the whole network jointly. Here, we introduce a general‐purpose network‐wide phase picking algorithm based on a recently developed machine learning paradigm called Neural Operator. Our model, called Phase Neural Operator, leverages the spatio‐temporal contextual information to pick phases simultaneously for any seismic network geometry. This results in superior performance over leading baseline algorithms by detecting many more earthquakes, picking more phase arrivals, while also greatly improving measurement accuracy. Following similar trends being seen across the domains of artificial intelligence, our approach provides but a glimpse of the potential gains from fully‐utilizing the massive seismic data sets being collected worldwide. Plain Language Summary Earthquake monitoring often involves measuring arrival times of P‐ and S‐waves of earthquakes from continuous seismic data. With the advancement of artificial intelligence, state‐of‐the‐art phase picking methods use deep neural networks to examine seismic data from each station independently; this is in stark contrast to the way that human experts annotate seismic data, in which waveforms from the whole network containing multiple stations are examined simultaneously. With the performance gains of single‐station algorithms approaching saturation, it is clear that meaningful future advances will require algorithms that can naturally examine data for entire networks at once. Here we introduce a multi‐station phase picking algorithm based on a recently developed machine learning paradigm called Neural Operator. Our algorithm, called Phase Neural Operator, leverages the spatial‐temporal information of earthquake signals from an input seismic network with arbitrary geometry. This results in superior performance over leading baseline algorithms by detecting many more earthquakes, picking many more seismic wave arrivals, yet also greatly improving measurement accuracy. Key Points We introduce a multi‐station phase picking algorithm, Phase Neural Operator (PhaseNO), that is based on a new machine learning paradigm called Neural Operator PhaseNO can use data from any number of stations arranged in any arbitrary geometry to pick phases across the input stations simultaneously By leveraging the spatial and temporal contextual information, PhaseNO achieves superior performance over leading baseline algorithms

The seismic crisis that began in May, 2018 off the coast of Mayotte announced the onset of a volcanic eruption that started two months later 50 km southeast of the island. This seismicity has since been taken as an indicator of the volcanic and tectonic activity in the area. In response to this activity, a network of stations was deployed on Mayotte over the past three years. We used the machine learning-based method PhaseNet to re-analyze the seismicity recorded on land since March 2019. We detect 50,512 events compared to around 6508 manually picked events between March 2019 and March 2021. We locate them with NonLinLoc and a locally developed 1-D velocity model. While eruptions are often monitored through the analysis of Volcano-Tectonic (VT) seismicity (2–40 Hz), we focus on the lower frequency, Long Period (LP) earthquakes (0.5–5 Hz), which are thought to be more directly related to fluid movement at depth. In Mayotte, the VT events are spread between two clusters, whereas the LP events are all located in a single cluster in the bigger proximal VT cluster, at depths ranging from 25 to 40 km. Moreover, while the VT earthquakes of the proximal cluster occur continuously with no apparent pattern, LP events occur in swarms that last for tens of minutes. We show that during the swarms, LP events generally migrate downward at a speed of 5 m/s. While these events do not appear directly linked to upward fluid migration, their waveform signature could result from propagation through a fluid-rich medium. They occur at a different location than VT earthquakes, also suggesting a different origin which could be linked to the Very Long Period events (VLP) observed above the LP earthquakes in Mayotte.

The application of deep‐learning‐based seismic phase pickers has surged in recent years. However, the efficacy of these models when applied to monitoring volcano seismicity has yet to be fully evaluated. Here, we first compile a data set of seismic waveforms from various volcanoes globally. We then show that the performances of two widely used deep‐learning pickers deteriorate systematically as the earthquakes' frequency content decreases. Therefore, the performances are especially poor for long‐period earthquakes often associated with fluid/magma movement. Subsequently, we train new models which perform significantly better, including when tested on two data sets where no training data were used: volcanic earthquakes along the Cascadia subduction zone and tectonic low‐frequency earthquakes along the Nankai Trough. Our model/workflow can be applied to improve monitoring of volcano seismicity globally while our compiled data set can be used to benchmark future methods for characterizing volcano seismicity, especially long‐period earthquakes which are difficult to monitor. Plain Language Summary Earthquake activity at volcanic regions is often monitored to indicate volcanic activity. Identifying the time when the energy radiated from an earthquake source arrives at a seismometer is essential for locating the earthquake, which can be difficult for volcanic earthquakes because of high noise levels, high event rates, and obscured onsets. Previous studies have demonstrated that deep learning can excel in picking the arrival times of regular earthquakes. However, it is unclear how sensitive these detectors are to earthquakes in volcanic regions. Here, we first compile a data set of earthquakes from various volcanoes globally. We then show that existing deep‐learning‐based detectors can miss a large fraction of these earthquakes, especially those without an abrupt change in signal amplitude. We then provide two new models which can better detect volcanic earthquakes than existing models. Our model/workflow can be applied to improve monitoring of volcanic earthquakes globally. Key Points We compile a data set of seismic waveforms from various volcanic regions globally We show that existing deep‐learning phase pickers' performances deteriorate with decreasing earthquake frequency content Our retrained models perform better and are more generalizable for monitoring volcano seismicity, especially long‐period earthquakes

In this study, we build a multi‐station phase‐picking model named EdgePhase by integrating an Edge Convolutional module with a state‐of‐the‐art single‐station phase‐picking model, EQTransformer. The Edge Convolutional module, a variant of Graph Neural Network, exchanges information relevant to seismic phases between neighboring stations. In EdgePhase, seismograms are first encoded into the latent representations, then converted into enhanced representations by the Edge Convolutional module, and finally decoded into the P‐ and S‐phase probabilities. Compared to the standard EQTransformer, EdgePhase increases the precision (fraction of phase identifications that are real) and recall (fraction of phase arrivals that are identified) rate by 5% on our training and test data sets of Southern California earthquakes. To evaluate its performance in regions of different tectonic settings, we applied EdgePhase to detect the early aftershocks following the 2020 M7.0 Samos, Greece earthquake. Compared to a local earthquake catalog, EdgePhase produced 190% additional detections with an event distribution more conformative to a planar fault interface, suggesting higher fidelity in event locations. This case study indicates that EdgePhase provides a strong regional generalization capability in real‐world applications. Plain Language Summary Identifying seismic phases from continuous waveforms is an important task for earthquake monitoring and early warning systems. Traditional phase recognition methods include visual inspection and detections based on mathematical functions (e.g., STA/LTA, kurtosis, AIC). Recently, machine learning technology has been applied to this task because of its fast operation speed and complete automation. A variety of neural‐network‐based models take the waveforms of a single station as input and predict the P‐phases and S‐phases. In this study, we improve the model performance by taking into account the mutually consistent features in multiple stations. We incorporate a Graph Neural Network module to exchange information relevant to seismic phases between neighboring stations. Compared to the standard single station model, our multi‐station model performs better on seismic data in Southern California in terms of the precision and recall rate. We also tested our model on the 2020 M7.0 Greece, Samos Earthquake and found that it detected significantly more aftershocks compared to local catalogs in the first month after the mainshock. Key Points We developed EdgePhase, a multi‐station phase‐picking model, by fine‐tuning EQTransformer with Graphic Neural Networks Compared to the standard EQTransformer, EdgePhase increases the F1 score by 5% on the Southern California Seismic data set Performance evaluation of EdgePhase shows its strong generalization ability in real‐world applications

The detection and monitoring of mining-induced seismicity are essential for understanding the mechanisms behind earthquakes and mitigating seismic hazards. However, traditional underground seismic monitoring networks for mining-induced seismicity are challenging to install and operate, which has limited their widespread application. In recent years, an alternative approach has emerged: utilizing dense seismic arrays at the surface to monitor mining-induced seismicity. This paper proposes a rapid and efficient data processing scheme for the detection and monitoring of mining-induced seismicity based on the surface dense array. The proposed workflow includes machine learning-based phase picking and P-wave first-motion-polarity picking, followed by rapid phase association, precise earthquake location, and template matching for detecting small earthquakes to enhance the completeness of the earthquake catalog. Additionally, it also provides focal mechanism solutions for larger mining-induced events. We applied this workflow to the continuous waveform data from 90 seismic stations over a period of 27 days around the Dongchuan Copper Mine, Yunnan Province, China. Our results yielded 1536 high-quality earthquake locations and two focal mechanism solutions for larger events. By analyzing the spatiotemporal distribution of these events, we are able to investigate the mechanisms of the induced seismic clusters near the Shijiangjun and Lanniping deposits. Our findings highlight the excellent monitoring capability and application potential of the workflow based on machine learning and template matching compared with conventional techniques.

Seismic phase picking is a fundamental task in seismology that is crucial for event detection and earthquake cataloging; however, manual analysis is impractical given the scale of modern seismic networks. We present SegPhase, a novel seismic arrival time picking model designed to efficiently process large-scale seismic data recorded by dense seismic networks in Japan. In contrast to conventional convolution-based models, SegPhase employs a hierarchical vision transformer structure that utilizes multi-head self-attention to dynamically focus on important waveform features, such as P- and S-wave onsets, noise, and coda waves. Compared to PhaseNet, the most widely used deep learning model, SegPhase improved arrival time match rates by ~ 11% and detected ~ 15% more events in continuous waveform tests, particularly enhancing the detection of small-magnitude events. Benchmark evaluations demonstrated that SegPhase achieved high classification performance in identifying P- and S-waves. We also examined the threshold of the output probability values when applying SegPhase to continuous waveforms for which the optimal threshold was unknown. By lowering the threshold to 0.1, we observed an increase in the number of detected events without noticeable changes in the hypocenter location error and observed–calculated discrepancies. This was achieved by more effectively utilizing high-probability picks, which further improved phase association. Based on these results, we recommend a threshold of 0.1 to enhance event detection while maintaining accurate arrival times. Our findings demonstrate that SegPhase enables robust arrival picking across diverse datasets and supports high-resolution seismic monitoring. Graphical Abstract

In this paper, we propose a new approach based on the fitting of a generalized linear regression model in order to detect points of change in the variance of a multivariate-covariance Gaussian variable, where the variance function is piecewise constant. By applying this new approach to multivariate waveforms, our method provides simultaneous detection of change points in functional time series. The proposed approach can be used as a new picking algorithm in order to automatically identify the arrival times of P- and S-waves in different seismograms that are recording the same seismic event. A seismogram is a record of ground motion at a measuring station as a function of time, and it typically records motions along three orthogonal axes (X, Y, and Z), with the Z-axis being perpendicular to the Earth’s surface and the X- and Y-axes being parallel to the surface and generally oriented in North–South and East–West directions, respectively. The proposed method was tested on a dataset of simulated waveforms in order to capture changes in the performance according to the waveform characteristics. In an application to real seismic data, our results demonstrated the ability of the multivariate algorithm to pick the arrival times in quite noisy waveforms coming from seismic events with low magnitudes.

Artificial intelligence (AI) has emerged as a crucial tool in the monitoring and research of anthropogenic earthquakes (AEs). Despite its utility, AEs monitoring faces significant challenges due to the intricate signal characteristics of seismic events, low signal-to-noise ratio (SNR) in data, and insufficient spatial coverage of monitoring networks, which complicate the effective deployment of AI technologies. This review systematically explores recent advancements in AI applications for identifying and classifying AEs, detecting weak signals, phase picking, event localization, and seismic risk analysis, while highlighting current issues and future developmental directions. Key challenges include accurately distinguishing specific anthropogenic seismic events due to their intricate signal patterns, limited model generalizability caused by constrained training datasets, and the lack of comprehensive models capable of handling event recognition, detection, and classification across diverse scenarios. Despite these obstacles, innovative approaches such as data-sharing platforms, transfer learning (TL), and hybrid AI models offer promising solutions to enhance AEs monitoring and improve predictive capabilities for induced seismic hazards. This review provides a scientific foundation to guide the ongoing development and application of AI technologies in AEs monitoring, forecasting, and disaster mitigation.

Acoustic emissions (AEs) are bursts of elastic waves generated by ruptures in laboratory rock mechanics experiments that mirror typical seismograms recorded in natural earthquakes, albeit at much higher frequencies. Traditionally, AE events were manually sorted and picked—a time-consuming and daunting task. Recently, automatic methods based on machine learning (ML) or template matching have been applied to detect AE events. In order to accurately and quickly analyze a large quantity of raw AE waveforms, the current study explores the direct application of ML tools designed for regular earthquake waveforms to the AE detection and picking process. We investigated applications of a deep-learning-based detector EQTransformer (EQT) that was trained on global earthquake data to laboratory AE datasets without retraining. Two AE datasets were collected from laboratory deformation experiments during the syn-deformational phase transformation from olivine to spinel in Mg 2 GeO 4 . We compared EQT’s performance on AEs to its published performance on natural earthquakes, as well as to a neural network (NN) designed for AE detection and picking called MultiNet. When applied to dataset D2540, EQT detected all 3901 previously identified events in the dataset with a mean P -pick error of < 1 sampling point, in addition to 2521 previously undetected events. For dataset D1247, EQT also detected all 550 known events with a mean error of < 1 sampling point, as well as 22 new events. In both cases, EQT performed within the standards advertised for EQT on earthquake data and with similar precision to MultiNet. Our results indicate that the EQT model pre-trained using global seismic data can be directly applied to accurately pick AE events in laboratory settings, with robust performance across multiple recording channels. Graphical Abstract