Search Results (588)

Advancing the capabilities of earthquake nowcasting, the real-time forecasting of seismic activities, remains crucial for reducing casualties. This multifaceted challenge has recently gained attention within the deep learning domain, facilitated by the availability of extensive earthquake datasets. Despite significant advancements, the existing literature on earthquake nowcasting lacks comprehensive evaluations of pre-trained foundation models and modern deep learning architectures; each focuses on a different aspect of data, such as spatial relationships, temporal patterns, and multi-scale dependencies. This paper addresses the mentioned gap by analyzing different architectures and introducing two innovative approaches called Multi Foundation Quake and GNNCoder. We formulate earthquake nowcasting as a time series forecasting problem for the next 14 days within 0.1-degree spatial bins in Southern California. Earthquake time series are generated using the logarithm energy released by quakes, spanning 1986 to 2024. Our comprehensive evaluations demonstrate that our introduced models outperform other custom architectures by effectively capturing temporal-spatial relationships inherent in seismic data. The performance of existing foundation models varies significantly based on the pre-training datasets, emphasizing the need for careful dataset selection. However, we introduce a novel method, Multi Foundation Quake, that achieves the best overall performance by combining a bespoke pattern with Foundation model results handled as auxiliary streams. Full article

The structural integrity of buried pipelines is threatened by the effects of Permanent Ground Deformation (PGD), resulting from seismic-induced landslides and lateral spreading due to liquefaction, requiring accurate analysis of the system performance. Analytical fragility functions allow us to estimate the likelihood of seismic damage along the pipeline, supporting design engineers and network operators in prioritizing resource allocation for mitigative or remedial measures in spatially distributed lifeline systems. To efficiently and accurately evaluate the seismic fragility of a buried operating steel pipeline under longitudinal PGD, this study develops a new analytical model, accounting for the asymmetric pipeline behavior in tension and compression under varying operational loads. This validated model is further implemented within a fragility function calculation framework based on the Monte Carlo Simulation (MCS), allowing us to efficiently assess the probability of the pipeline exceeding the performance limit states, conditioned to the PGD demand. The evaluated fragility surfaces showed that the probability of the pipeline exceeding the performance criteria increases for larger soil displacements and lengths, as well as cover depths, because of the greater mobilized soil reaction counteracting the pipeline deformation. The performed Global Sensitivity Analysis (GSA) highlighted the influence of the PGD and soil–pipeline interaction parameters, as well as the effect of the service loads on structural performance, requiring proper consideration in pipeline system modeling and design. Overall, the proposed analytical fragility function calculation framework provides a useful methodology for effectively assessing the performance of operating pipelines under longitudinal PGD, quantifying the effect of the uncertain parameters impacting system response. Full article

Modern, large bridges and tunnels represent important nodes in transportation arteries and have a significant impact on the development of transportation. The health and safety monitoring of these structures has always been a significant concern and is reliant on various types of sensors. Distributed acoustic sensing (DAS) with telecommunication fibers is an emerging technology in the research areas of sensing and communication. DAS provides an effective and low-cost approach for the detection of various resources and seismic activities. In this study, field experiments are elucidated, using DAS for the Hong Kong–Zhuhai–Macao Bridge, and for studying vehicle trajectories, earthquakes, and other activities. The basic signal-processing methods of filtering and normalization are adopted for analyzing the data obtained with DAS. With the proposed DAS technology, the activities on shore, vehicle trajectories on bridges and in tunnels during both day and night, and microseisms within 200 km were successfully detected. Enabled by DAS technology and mass fiber networks, more studies on sensing and communication systems for the monitoring of bridge and tunnel engineering are expected to provide future insights. Full article

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. Full article

This study compares the effectiveness of different methods for coal thickness identification, aiming to identify the most accurate approach and provide a reference for intelligent coalmine development. Focused on the No. 2 coal seam in a mining area in Shanxi, China, the analysis employs well log-constrained impedance inversion and seismic multi-attribute techniques. The results show that the back propagation (BP) neural network model, as part of the seismic multi-attribute approach, delivers prediction accuracy comparable to the well log-constrained inversion method. Specifically, after applying proper static corrections, a four-layer BP neural network was constructed using four optimized sensitive attributes as the input layer, achieving an error range of 0.11% to 1.36%, compared to 0.03% to 6.59% for the logging-based method. The BP neural network demonstrated strong applicability in complex geological environments. Empirical analysis further validated the BP neural network’s geological reliability and practicality in systematic coal thickness determination. Full article

Although the wind load is usually adopted as the governing lateral load in the design of transmission towers, many tall transmission towers may be damaged or even collapse in high seismic intensity areas, especially under near-fault pulse-like ground motions. To study the seismic vibration control effect of a tuned mass damper (TMD) attached to transmission tower, parametric analyses are conducted in SAP2000 through CSI OAPI programming, including TMD parameters such as the mass ratio μ from 0.5% to 10%, the frequency ratio f from 0.7 to 1.2, and the damping ratio ξ from 0.01 to 0.2. Based on the obtained analysis results, artificial neural network (ANN) is trained to predict the vibration reduction ratios of peak responses and the corresponding vibration reduction cost. Finally, the NSGA-III algorithm is adopted to perform the multi-objective optimization of a transmission tower equipped with TMD. Results show that the vibration reduction ratios first increase and then decrease with the increase of frequency ratio, but first increase and then remain stable with the increase of mass ratio and damping ratio. In addition, ANN fitting can accurately predict the nonlinear relationship between TMD parameters and objective functions. Through multi-objective optimization with the NSGA-III algorithm, TMD can simultaneously and significantly reduce different peak responses of transmission towers under near-fault pulse-like ground motions in a cost-effective manner. Full article

A scientific and reasonable microseismic monitoring sensor network is crucial for the prevention and control of rockmass instability disasters. In this study, three feasible sensor network layout schemes for the microseismic monitoring of Sanshandao Gold Mine were proposed, comprehensively considering factors such as orebody orientation, tunnel and stope distributions, blasting excavation areas, construction difficulty, and maintenance costs. To evaluate and validate the monitoring effectiveness of the sensor networks, three layers of seismic sources were randomly generated within the network. Four levels of random errors were added to the calculated arrival time data, and the classical Geiger localization algorithm was used for locating validation. The distribution of localization errors within the monitoring area was analyzed. The results indicate that when the arrival time data are accurate or the error is between 0% and 2%, scheme 3 is considered the most suitable layout; when the error of the arrival time data is between 2% and 10%, scheme 2 is considered the optimal layout. These research results can provide important theoretical and technical guidance for the reasonable design of microseismic monitoring systems in similar mines or projects. Full article

Accurate deblending techniques are essential for the successful application of blended seismic acquisition. Deep-learning-based deblending methods typically begin by performing a pseudo-deblending operation on blended data, followed by further processing in either the common-shot domain or a non-common-shot domain. In this study, we propose an iterative deblending framework based on deep learning, which directly addresses the blended data in the shot domain, eliminating the need for pseudo-deblending and domain transformation. This framework is built around a unique architecture, termed WNETR, which derives its name from its W-shaped network structure that combines U-Net and Transformer. During testing, the trained WNETR is incorporated into the iterative framework to extract useful signals iteratively. Tests on synthetic data validate the effectiveness of the proposed deblending iterative framework. Full article

Noise reduction is a critical step in seismic data processing. A novel strong noise reduction network is proposed in this study. The network enhances the U-Net architecture with an improved inception module and coordinate attention (CA) mechanism, suppressing noise and enhancing signal clarity. These enhancements improve the network’s capability to distinguish between signal and noise in the time–frequency domain. We trained and tested our model on the STEAD dataset, which eliminated noise across various frequency bands, improved the signal-to-noise ratio (SNR) of seismic records, and reduced the waveform distortion significantly. Comparative analyses against U-Net, DeepDenoiser, and DnRDB models, using signals with SNRs ranging from −14 dB to 0 dB, demonstrated our model’s superior performance. At the same time, we demonstrated that the Inception Conv Block has a significant impact on the denoising ability of the network. Furthermore, validation using the “Di Ting” dataset and real noisy signals confirmed the model’s generalizability. These results show that the proposed model significantly outperforms the comparative methods in terms of the SNR, correlation coefficient (r), and root mean square error (RMSE), delivering higher-quality seismograms. The enhanced phase-picking accuracy underscores the potential of our approach to advance in geophysics applications. Full article

Over the last decade, distributed acoustic sensing (DAS) has received growing attention in the field of seismic acquisition and monitoring due to its potential high spatial sampling rate, low maintenance cost and high resistance to temperature and pressure. Despite its undeniable advantages, DAS faces some challenges, including a low signal-to-noise ratio, which partly results from the instrument-specific noise generated by DAS interrogators. We present a comparison between two deep learning approaches to address DAS hardware noise and enhance the quality of DAS data. These approaches have the advantage of including real instrumental noise in the neural network training dataset. For the supervised learning (SL) approach, real DAS instrumental noise measured on an acoustically isolated coil is added to synthetic data to generate training pairs of clean/noisy data. For the second method, the Noise2Noise (N2N) approach, the training is performed on noisy/noisy data pairs recorded simultaneously on the downgoing and upgoing parts of a downhole fiber-optic cable. Both approaches allow for the removal of unwanted noise that lies within the same frequency band of the useful signal, a result that cannot be achieved by conventional denoising techniques employing frequency filtering. Full article

In this study, we used machine learning (ML) to estimate time-lapse velocity variations in a reservoir region using seismic data. To accomplish this task, we needed an adequate training set that could map seismic data to velocity perturbation. We generated a synthetic seismic database by simulating reservoirs of varying velocities using a 2D velocity model typical of the Brazilian pre-salt ocean bottom node (OBN) acquisition, located in the Santos basin, Brazil. The largest velocity change in the injector well was around 3% of the empirical velocity model, which mimicked a realistic scenario. The acquisition geometry was formed by the geometry of 1 shot and 49 receivers. For each synthetic reservoir, the corresponding seismic data were obtained by estimating a one-shot forward-wave propagation using acoustic approximation. We studied the reservoir illumination to optimize the input data of the ML inversion. We split the set of synthetic reservoirs into two subsets: training (80%) and testing (20%) sets. We point out that the ML inversion was restricted to the reservoir zone, which means that it was inversion-oriented to a target. We obtained a good similarity between true and ML-inverted reservoir anomalies. The similarity diminished for a situation with non-repeatability noise. Full article

Tsunamis are devastating natural phenomena that cause extensive damage to both human life and infrastructure. To mitigate such impacts, tsunami early warning systems have been deployed globally. South Korea has also initiated a project to install a tsunami warning system to monitor its surrounding seas. To ensure reliable warning decisions, various types of data must be combined, but efficiently transmitting heterogeneous data poses a challenge due to the unique characteristics of underwater acoustic communication. Therefore, this paper proposes a Hybrid Duplex Medium Access Control (HDMAC) protocol designed for a tsunami warning system, with a specific focus on heterogeneous data transmission. HDMAC efficiently handles both seismic and environmental data by utilizing hybrid duplexing, which combines frequency duplex for seismic data with time duplex for environmental data. The protocol addresses the distinct transmission requirements for each data type by optimizing channel utilization through a group Automatic Repeat request (ARQ) scheme and packet size adjustment. Theoretical analysis predicts that HDMAC can achieve a channel utilization of up to 0.91 in smaller networks and 0.64 in larger networks. HDMAC is validated through simulations, and the simulation results closely match these predictions. The simulation results demonstrate the efficiency of HDMAC in supporting real-time submarine earthquake monitoring systems. Full article

In this study, the topological properties of the shallow seismicity occurring in the area around the Lai Chau hydropower plant (Vietnam) are investigated by using visibility graph (VG) analysis, a well-known method to convert time series into networks or graphs. The relationship between the seismicity and reservoir water level was analyzed using Interlayer Mutual Information (IMI) and the Frobenius norm, both applied to the corresponding VG networks. IMI was used to assess the correlation between the two variables, while the Frobenius norm was employed to estimate the time delay between them. The total seismicity, which resulted in an $M\ge 0.8$ with a b-value of 0.86, is characterized by a $k-M$ slope of ≈9.1. Analyzing the variation of the seismological and topological parameters of the seismicity relative to the distance from the center of the Lai Chau reservoir revealed the following features: (1) the b-value fluctuates around a mean value of 1.21 at distances of up to 10–11 km, while, for distances larger than 25–30 km, it tends to the value of 0.86; (2) the maximum IMI between the monthly number of earthquakes and the monthly mean water level occurs at a distance of 9–11 km, showing a distance evolution similar to that of the b-value; (3) at these distances from the center of the reservoir, the time lag between the earthquake monthly counts and the monthly water level mean is 9–10 months; (4) the relationship between the b-value and the $k-M$ slope suggests that the $k-M$ slope depends on the number of earthquakes within a 22 km radius from the center of the dam. Our study’s findings offer new insights into the complex dynamics of seismicity occurring around reservoirs. Full article

Seismic data processing plays a pivotal role in extracting valuable subsurface information for various geophysical applications. However, seismic records often suffer from inherent random noise, which obscures meaningful geological features and reduces the reliability of interpretations. In recent years, deep learning methodologies have shown promising results in performing noise attenuation tasks on seismic data. In this research, we propose modifications to the standard U-Net structure by integrating dense and residual connections, which serve as the foundation of our approach named the dense and residual (DARE U-Net) network. Dense connections enhance the receptive field and ensure that information from different scales is considered during the denoising process. Our model implements local residual connections between layers within the encoder, which allows earlier layers to directly connect with deep layers. This promotes the flow of information, allowing the network to utilize filtered and unfiltered input. The combined network mechanisms preserve the spatial information loss during the contraction process so that the decoder can locate the features more accurately by retaining the high-resolution features, enabling precise location in seismic image denoising. We evaluate this adapted architecture by applying synthetic and real data sets and calculating the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). The effectiveness of this method is well noted. Full article

Exploring shallow mineral resources requires acquiring denser seismic data, for which Distributed Acoustic Sensing is an effective enabler and relevant to mining operations monitoring. Passive seismic can be of interest in characterizing the subsurface; however, dealing with large amounts of data pushes against the limits of existing computational systems and algorithms, especially for continuous monitoring. Hence, more than ever, novel data analysis methods are needed. In this article, we investigate using synthetic seismic data, paired with real noise recordings, as part of a supervised deep-learning neural network methodology to detect and locate induced seismic sources and explore their potential use to reconstruct subsurface properties. Challenges of this methodology were identified and addressed in the context of induced seismicity applications. Data acquisition and modelling were discussed, preparation workflows were implemented, and the method was demonstrated on synthetic data and tested on relevant seismic monitoring field dataset from the Otway CO₂ injection site. Conducted tests confirmed the effects of time shifts, signal-to-noise ratios, and geometry mismatches on the performance of trained models. Those promising results showed the method’s applicability and paved the way for potential application to more field data, such as seismic while drilling. Full article