Search Results (76)

Microseismic monitoring has become a critical technology for hydraulic fracturing in unconventional oil and gas reservoirs, owing to its high temporal and spatial resolution. It plays a pivotal role in tracking fracture propagation and evaluating stimulation effectiveness. However, the automatic picking of first-arrival times and accurate source localization remain challenging under complex noise conditions, which constrain the reliability of fracture parameter inversion and reservoir assessment. To address these limitations, we propose a hybrid approach that combines optimized variational mode decomposition (OVMD), wavelet thresholding denoising (WTD), and an adaptive fractal box-counting dimension algorithm for enhanced first-arrival picking and source localization. Specifically, OVMD is first employed to adaptively decompose seismic signals and isolate noise-dominated components. Subsequently, WTD is applied in the multi-scale frequency domain to suppress residual noise. An adaptive fractal dimension strategy is then utilized to detect change points and accurately determine the first-arrival time. These results are used as inputs to a particle swarm optimization (PSO) algorithm for source localization. Both numerical simulations and laboratory experiments demonstrate that the proposed method exhibits high robustness and localization accuracy under severe noise conditions. It significantly outperforms conventional approaches such as short-time Fourier transform (STFT) and continuous wavelet transform (CWT). The proposed framework offers reliable technical support for dynamic fracture monitoring, detailed reservoir characterization, and risk mitigation in the development of unconventional reservoirs. Full article

Most public seismic recordings, sampled at hundreds of Hz, tend to be unlabelled, i.e., not catalogued, mainly because of the sheer volume of samples and the amount of time needed by experts to confidently label detected events. This is especially challenging for very low signal-to-noise ratio microseismic events that characterise landslides during rock and soil mass displacement. Whilst numerous supervised machine learning models have been proposed to classify landslide events, they rely on a large amount of labelled datasets. Therefore, there is an urgent need to develop tools to effectively automate the data-labelling process from a small set of labelled samples. In this paper, we propose a semi-supervised method for labelling of signals recorded by seismometers that can reduce the time and expertise needed to create fully annotated datasets. The proposed Siamese network approach learns best class-exemplar anchors, leveraging learned similarity between these anchor embeddings and unlabelled signals. Classification is performed via soft-labelling and thresholding instead of hard class boundaries. Furthermore, network output explainability is used to explain misclassifications and we demonstrate the effect of anchors on performance, via ablation studies. The proposed approach classifies four landslide classes, namely earthquakes, micro-quakes, rockfall and anthropogenic noise, demonstrating good agreement with manually detected events while requiring few training data to be effective, hence reducing the time needed for labelling and updating models. Full article

This study focuses on the multiphase flow in horizontal wells based on distributed acoustic sensing (DAS) monitoring. Through laboratory experiments and field data analysis, it was found that the micro-seismic differences in flow patterns can be clearly observed in the fiber optic micro-seismic waterfall chart. In the case of slug flow, the DAS acoustic energy decreases when the inclination angle increases. The performance of annular flow is similar to that of bubble flow, with the DAS energy increasing as the inclination angle increases. Overall, the order of DAS acoustic energy from the strongest to weakest is slug flow, followed by annular flow, and then bubble flow. The research shows that fiber optic DAS monitoring signals can effectively identify differences in gas volume, well inclination, and flow pattern, which provides an important technical basis and research foundation for the monitoring and analysis of multiphase flow in horizontal wells. Full article

To improve the efficiency and accuracy of microseismic event extraction from time-series data and enhance the detection of anomalous events, this paper proposes a Multi-scale Fusion Convolution and Dilated Convolution Autoencoder (MDCAE) combined with a Constraint Shape-Based Distance algorithm incorporating volatility (CSBD-Vol). MDCAE extracts low-dimensional features from waveform signals through multi-scale fusion and dilated convolutions while introducing the concept of waveform volatility (Vol) to capture variations in microseismic waveforms. An improved Shape-Based Distance (SBD) algorithm is then employed to measure the similarity of these features. Experimental results on a microseismic dataset from the 802 working faces of a mining site demonstrate that the CSBD-Vol algorithm significantly outperforms SBD, Shape-Based Distance with volatility (SBD-Vol), and Constraint Shape-Based Distance (CSBD) in classification accuracy, verifying the effectiveness of constrained time windows and volatility in enhancing performance. The proposed clustering algorithm reduces time complexity from $O\left(n^2\right)$ to $O(nlogn)$, achieving substantial improvements in computational efficiency. Furthermore, the MDCAE-CSBD-Vol approach achieves 87% accuracy in microseismic time-series waveform classification. These findings highlight that MDCAE-CSBD-Vol offers a novel, precise, and efficient solution for detecting anomalous events in microseismic systems, providing valuable support for accurate and high-efficiency monitoring in mining and related applications. Full article

Coal mine disaster safety monitoring often employs microseismic technology for its high sensitivity and real-time capability. However, nonlinear, non-stationary, and multi-scale signals limit traditional time series models (e.g., ARMA, ARIMA). This paper proposes a hybrid deep learning model—VMD-SE-CEEMDAN-BO-CNNGRU—integrating variational mode decomposition, sample entropy, CEEMDAN, Bayesian optimization, and a CNN-GRU architecture. Microseismic data from the 08 working face in D mine (Weibei mining area) were used to predict daily maximum energy, average energy, and frequency. The model achieved high predictive performance with R² values of 0.93, 0.89, and 0.88, significantly outperforming baseline models lacking modal decomposition. Comparative experiments verified the superiority of the VMD-first, SE-reconstruction, and CEEMDAN-second decomposition strategy, yielding up to 13% greater accuracy than reverse-order schemes. The model maintained R² above 0.80 on another dataset from the 03 working face in W mine (Binchang mining area), demonstrating robust generalization. Although performance declined during fault disturbances, accuracy for average energy and frequency rebounded post-disturbance, indicating strong adaptability. Overall, the VSCB-CNNGRU model enhances both accuracy and stability in microseismic prediction, supporting dynamic risk assessment and early warning in coal mining. Full article

Distributed Acoustic Sensing (DAS) has emerged as a groundbreaking technology in seismology, transforming fiber-optic cables into dense, cost-effective seismic monitoring arrays. DAS makes use of Rayleigh backscattering to detect and measure dynamic strain and vibrations over extended distances. It can operate using both pre-existing telecommunication networks and specially designed fibers. This review explores the principles of DAS, including Coherent Optical Time Domain Reflectometry (COTDR) and Phase-Sensitive OTDR (ϕ-OTDR), and discusses the role of optoelectronic interrogators in data acquisition. It examines recent advancements in fiber design, such as helically wound and engineered fibers, which improve DAS sensitivity, spatial resolution, and the signal-to-noise ratio (SNR). Additionally, innovations in deployment techniques include cemented borehole cables, flexible liners, and weighted surface coupling to further enhance mechanical coupling and data accuracy. This review also demonstrated the applications of DAS across earthquake detection, microseismic monitoring, reservoir characterization and monitoring, carbon storage sites, geothermal reservoirs, marine environments, and urban infrastructure surveillance. The study highlighted several challenges of DAS, including directional sensitivity limitations, vast data volumes, and calibration inconsistencies. It also addressed solutions to these problems, such as advances in signal processing, noise suppression techniques, and machine learning integration, which have improved real-time analysis and data interpretability, enabling DAS to compete with traditional seismic networks. Additionally, modeling approaches such as full waveform inversion and forward simulations provide valuable insights into subsurface dynamics and fracture monitoring. This review highlights DAS’s potential to revolutionize seismic monitoring through its scalability, cost-efficiency, and adaptability to diverse applications while identifying future research directions to address its limitations and expand its capabilities. Full article

Distributed Acoustic Sensing (DAS) offers numerous advantages, including resistance to electromagnetic interference, long-range dynamic monitoring, dense spatial sensing, and low deployment costs. We initially deployed a water–land DAS system at the Xinfengjiang (XFJ) Reservoir in Guangdong Province, China, to monitor earthquake events. Environmental noise analysis identified three distinct noise zones based on deployment conditions: periodic 18 Hz signals near surface-laid segments, attenuated low-frequency signals (<10 Hz) in the buried terrestrial sections, and elevated noise at transition zones due to water–cable interactions. The system successfully detected hundreds of teleseismic and regional earthquakes, including a Mw7.3 earthquake in Hualien and a local ML0.5 microseismic event. One year later, the DAS system was upgraded with two types of spiral sensor cables at the end of the submarine cable, extending the total length to 5.51 km. The results of detecting both active (transducer) and passive sources (cooperative vessels) highlight the potential of integrating DAS interrogators with spiral sensor cables for the accurate tracking of underwater moving targets. This field trial demonstrates that DAS technology holds promise for the integrated joint monitoring of underwater acoustics and seismic signals beneath lake or ocean bottoms. Full article

In the process of unconventional oil and gas production, a large number of microseismic signals are generated. These signals are received by geophones deployed on the ground or in wells and used for safety monitoring. The moving-coil geophone is a commonly used geophone, which is widely used for collecting vibration signals. However, the current conventional moving-coil geophones have certain limitations in terms of frequency band range and cannot fully meet the low-frequency requirements of microseismic signals. We studied the structure and material properties of moving-coil geophones to understand the factors that affect their frequency band. In this paper, we use finite element analysis method to perform structural analysis on a 10 Hz moving-coil geophone, and we combine modal analysis and excitation response analysis to obtain its operating frequency range of 10.63–200.68 Hz. We then discuss the effect of the vibrating components of a moving-coil geophone on its operating frequency range. The material properties of the spring sheet mainly affect the natural frequency of the first-order mode (natural frequency, the lower limit of the operating frequency of the geophone), and the material properties of the lead spring mainly affect the natural frequency of the second-order mode (spurious frequency, the upper limit of the operating frequency of the geophone). By analyzing the sensitivity of the material properties of the vibration system parts and selecting more suitable spring sheets and lead spring materials, a lower natural frequency and a higher spurious frequency can be obtained, thereby achieving the purpose of broadening the operating frequency range of the geophone, which is expected to provide help in actual production. Full article

The construction of accurate anisotropic velocity models is essential for effective microseismic monitoring in hydraulic fracturing. Ignoring anisotropy can result in significant distortions in microseismic event locations and their interpretation. Although methods exist to simultaneously invert anisotropic parameters and event locations using microseismic arrival times, the results heavily depend on accurate initial models and sufficient ray coverage due to strong trade-offs among multiple parameters. Microseismic waveform inversion for anisotropic parameters remains challenging due to the low signal-to-noise ratio of the data and the high computational cost. To address these challenges, we propose a method for jointly inverting event locations and velocity updates based on arrival times and vertical slowness estimates, under the assumption of small horizontal velocity variations. Vertical slowness estimates, which are independent of source information and easily obtainable, provide an additional constraint that enhances inversion stability. We test the proposed method in four synthetic examples under various conditions. The results demonstrate that incorporating vertical slowness effectively constrains and stabilizes conventional travel-time inversion, especially in scenarios with poor raypath coverage. Additionally, we apply this method to a field case and find that it produces more reasonable event locations compared to inversions using arrival times alone. This joint inversion method can enhance the accuracy of anisotropic structures and event locations, which thus help with fracture characterization in tight and low-permeability reservoirs. It may serve as an effective downhole monitoring approach for hydrocarbon and geothermal energy production. Full article

As large-scale depletion of shallow coal seams and increasing mining depths intensify, the frequency and intensity of mining-induced earthquake events have significantly risen. Due to the complex formation mechanisms of high-energy mining-induced earthquakes, precise identification and early warning cannot be achieved with a single monitoring method, posing severe challenges to coal mine safety. Therefore, this study conducts an in-depth risk analysis of two high-energy mining-induced earthquake events at the 3308 working face of Yangcheng Coal Mine, integrating microseismic monitoring, stress monitoring, and seismic source mechanism analysis. The results show that, by combining microseismic monitoring, seismic source mechanism inversion, and dynamic stress analysis, critical disaster-inducing factors such as fault activation, high-stress concentration zones, and remnant coal pillars were successfully identified, further revealing the roles these factors play in triggering mining-induced earthquakes. Through multi-dimensional data integration, especially the effective detection of the microseismic “silent period” as a key precursor signal before high-energy mining-induced earthquake events, a critical basis for early warning is provided. Additionally, by analyzing the spatiotemporal distribution patterns of different risk factors, high-risk areas within the mining region were identified and delineated, laying a foundation for formulating precise prevention and control strategies. The findings of this study are of significant importance for mining-induced earthquake risk management, providing effective assurance for safe production in coal mines and other mining environments with high seismic risks. The proposed analysis methods and control strategies also offer valuable insights for seismic risk management in other mining industries, ensuring safe operations and minimizing potential losses. Full article

Construction projects in deep underground engineering are associated with the recording of massive amounts of diversified signals during real time and continuous microseismic monitoring given the complexity and specificity of the construction environment. Before the analysis of source information and further prediction of possible disasters, it is generally necessary to perform onset time picking and detection of microseismic signals. To improve the accuracy and efficiency of these tasks, this paper proposes an advanced deep dual-task neural network, which sequentially integrates the two processes. In this method, a score map is used to label the onset time of micro-fracture waveforms to improve the picking accuracy. The proposed model can simultaneously handle the onset time picking and detection tasks of microseismic signals to achieve optimal performance. Based on the similarity of data structures, the output from the onset time picking section is imported into the detection section to classify different types of microseismic waveforms. The onset time picking and detection procedures can be seamlessly integrated, where the score map of the onset time can help improve the detection accuracy. The results show that this method has a good performance for the onset time picking and detection of microseismic waveforms that are polluted by noises of various types and intensities. A comparison of the proposed method with existing methods and applications in underground engineering projects helped demonstrate the excellent performance of this method. The proposed approach can accelerate the automatic processing of microseismic signals and has significant potential for the exploration of seismology and earthquake research. Full article

Mine transboundary mining has been occurring frequently in recent years, and this illegal behavior has brought great potential danger to mine safety while also causing greater losses of state-owned assets. However, the current method of monitoring transboundary mining is still mainly based on underground verification by supervisors, which is far from meeting the demand for supervision. Microseismic monitoring technology is effective for monitoring transboundary mining due to its ability to locate vibration signals. For mine transboundary mining monitoring, this paper proposes a microseismic electronic fence method focusing on mine boundary locating, which differs from the routine microseismic monitoring used in mining operations. This method focuses its key monitoring area on the mine boundary. The deployment mode, number of sensors, and localization theory are analyzed, and numerical simulation and field measurement data analysis results show that the microseismic electronic fence method can achieve a localization accuracy of 15–20 m for underground microseismic events in the vicinity of mine boundaries, which can be effectively applied to the monitoring of transboundary mining activities. Full article

Borehole hydraulic fracturing in coal seams can prevent dynamic coal mine disasters and promote the sustainability of the mining industry, and microseismic signal recognition is a prerequisite and foundation for microseismic monitoring technology that evaluates the effectiveness of hydraulic fracturing. This study constructed ultra-lightweight CNN models specifically designed to identify microseismic waveforms induced by borehole hydraulic fracturing in coal seams, namely Ul-Inception28, Ul-ResNet12, Ul-MobileNet17, and Ul-TripleConv8. The three best-performing models were selected to create both a probability averaging ensemble CNN model and a voting ensemble CNN model. Additionally, an automatic threshold adjustment strategy for CNN identification was introduced. The relationships between feature map entropy, training data volume, and model performance were also analyzed. The results indicated that our in-house models surpassed the performance of the InceptionV3, ResNet50, and MobileNetV3 models from the TensorFlow Keras library. Notably, the voting ensemble CNN model achieved an improvement of at least 0.0452 in the F1 score compared to individual models. The automatic threshold adjustment strategy enhanced the identification threshold’s precision to 26 decimal places. However, a continuous zero-entropy value in the feature maps of various channels was found to detract from the model’s generalization performance. Moreover, the expanded training dataset, derived from thousands of waveforms, proved more compatible with CNN models comprising hundreds of thousands of parameters. The findings of this research significantly contribute to the prevention of dynamic coal mine disasters, potentially reducing casualties, economic losses, and promoting the sustainable progress of the coal mining industry. Full article

Three-section landslides are renowned for their immense size, concealed development process, and devastating impact. This study conducted physical model tests to simulate one special geological structure called a three-section-within landslide. The failure process and precursory characteristics of the tested samples were meticulously analyzed using video imagery, micro-seismic (MS) signals, and acoustic emission (AE) signals, with a focus on event activity, intensity, and frequency. A novel classification method based on AE waveform characteristics was proposed, categorizing AE signals into burst signals and continuous signals. The findings reveal distinct differences in the evolution of these signals. Burst signals appeared exclusively during the crack propagation and failure stages. During these stages, the cumulative AE hits of burst signals increased gradually, with amplitude rising and then declining. High-amplitude burst signals were predominantly distributed in the middle- and high-frequency bands. In contrast, cumulative AE hits of continuous signals escalated rapidly, with amplitude monotonously increasing, and high-amplitude continuous signals were primarily distributed in the low-frequency band. The emergence of burst signals and high-frequency AE signals indicated the generation of microcracks, serving as early-warning indicators. Notably, the early-warning points of AE signals were detected earlier than those of video imagery and MS signals. Furthermore, the early-warning point of burst signals occurred earlier than those of continuous signals, and the early-warning point of the classification method preceded that of overall AE signals. Full article

A deep-seated landslide could release numerous microseismic signals from creep-slip movement, which includes a rock-soil slip from the slope surface and a rock-soil shear rupture in the subsurface. Machine learning can effectively enhance the classification of microseismic signals in landslide seismic monitoring and interpret the mechanical processes of landslide motion. In this paper, eight sets of triaxial seismic sensors were deployed inside the deep-seated landslide, Jiuxianping, China, and a large number of microseismic signals related to the slope movement were obtained through 1-year-long continuous monitoring. All the data were passed through the seismic event identification mode, the ratio of the long-time average and short-time average. We selected 11 days of data, manually classified 4131 data into eight categories, and created a microseismic event database. Classical machine learning algorithms and ensemble learning algorithms were tested in this paper. In order to evaluate the seismic event classification performance of each algorithmic model, we evaluated the proposed algorithms through the dimensions of the accuracy, precision, and recall of each model. The validation results demonstrated that the best performing decision tree algorithm among the classical machine learning algorithms had an accuracy of 88.75%, while the ensemble algorithms, including random forest, Gradient Boosting Trees, Extreme Gradient Boosting, and Light Gradient Boosting Machine, had an accuracy range from 93.5% to 94.2% and also achieved better results in the combined evaluation of the precision, recall, and F1 score. The specific classification tests for each microseismic event category showed the same results. The results suggested that the ensemble learning algorithms show better results compared to the classical machine learning algorithms. Full article