Predicting microseismic,acoustic emission and electromagnetic radiation data using neural networks

Microseism,acoustic emission and electromagnetic radiation(M-A-E)data are usually used for predicting rockburst hazards.However,it is a great challenge to realize the prediction of M-A-E data.In this study,with the aid of a deep learning algorithm,a new method for the prediction of M-A-E data is proposed.In this method,an M-A-E data prediction model is built based on a variety of neural networks after analyzing numerous M-A-E data,and then the M-A-E data can be predicted.The predicted results are highly correlated with the real data collected in the field.Through field verification,the deep learning-based prediction method of M-A-E data provides quantitative prediction data for rockburst monitoring.

Transfer learning framework for multi-scale crack type classification with sparse microseismic networks

Rock fracture mechanisms can be inferred from moment tensors(MT)inverted from microseismic events.However,MT can only be inverted for events whose waveforms are acquired across a network of sensors.This is limiting for underground mines where the microseismic stations often lack azimuthal coverage.Thus,there is a need for a method to invert fracture mechanisms using waveforms acquired by a sparse microseismic network.Here,we present a novel,multi-scale framework to classify whether a rock crack contracts or dilates based on a single waveform.The framework consists of a deep learning model that is initially trained on 2400000+manually labelled field-scale seismic and microseismic waveforms acquired across 692 stations.Transfer learning is then applied to fine-tune the model on 300000+MT-labelled labscale acoustic emission waveforms from 39 individual experiments instrumented with different sensor layouts,loading,and rock types in training.The optimal model achieves over 86%F-score on unseen waveforms at both the lab-and field-scale.This model outperforms existing empirical methods in classification of rock fracture mechanisms monitored by a sparse microseismic network.This facilitates rapid assessment of,and early warning against,various rock engineering hazard such as induced earthquakes and rock bursts.

Analysis of rockburst mechanism and warning based on microseismic moment tensors and dynamic Bayesian networks

One of the major factors inhibiting the construction of deep underground projects is the risk posed by rockbursts.A study was conducted on the access tunnel of the Shuangjiangkou hydropower station to determine the evolutionary mechanism of microfractures within the surrounding rock mass during rockburst development and develop a rockburst warning model.The study area was chosen through the combination of field studies with an analysis of the spatial and temporal distribution of microseismic(MS)events.The moment tensor inversion method was adopted to study rockburst mechanism,and a dynamic Bayesian network(DBN)was applied to investigating the sensitivity of MS source parameters for rockburst warnings.A MS multivariable rockburst warning model was proposed and validated using two case studies.The results indicate that fractures in the surrounding rock mass during the development of strain-structure rockbursts initially show shear failure and are then followed by tensile failure.The effectiveness of the DBN-based rockburst warning model was demonstrated using self-validation and K-fold cross-validation.Moment magnitude and source radius are the most sensitive factors based on an investigation of the influence on the parent and child nodes in the model,which can serve as important standards for rockburst warnings.The proposed rockburst warning model was found to be effective when applied to two actual projects.

GPU-acceleration 3D rotated-staggered-grid solutions to microseismic anisotropic wave equation with moment tensor implementation

To improve the accuracy of microseismic inversion,seismic anisotropy and moment tensor source should be carefully considered in the forward modelling stage.In this study,3D microseismic anisotropy wave forward modelling with a moment tensor source was proposed.The modelling was carried out based on a rotated-staggered-grid(RSG)scheme.In contrast to staggered-grids,the RSG scheme defines the velocity components and densities at the same grid,as do the stress components and elastic parameters.Therefore,the elastic moduli do not need to be interpolated.In addition,the detailed formulation and implementation of moment-tensor source loaded on the RSG was presented by equating the source to the stress increments.Meanwhile,the RSG-based 3D wave equation forward modelling was performed in parallel using compute unified device architecture(CUDA)programming on a graphics processing unit(GPU)to improve its efficiency.Numerical simulations including homogeneous and anisotropic models were carried out using the method proposed in this paper,and compared with other methods to prove the reliability of this method.Furthermore,the high efficiency of the proposed approach was evaluated.The results show that the computational efficiency of proposed method can be improved by about two orders of magnitude compared with traditional central processing unit(CPU)computing methods.It could not only help the analysis of microseismic full wavefield records,but also provide support for passive source inversion,including location and focal mechanism inversion,and velocities inversion.

Microseismic event waveform classification using CNN-based transfer learning models

The efficient processing of large amounts of data collected by the microseismic monitoring system(MMS),especially the rapid identification of microseismic events in explosions and noise,is essential for mine disaster prevention.Currently,this work is primarily performed by skilled technicians,which results in severe workloads and inefficiency.In this paper,CNN-based transfer learning combined with computer vision technology was used to achieve automatic recognition and classification of multichannel microseismic signal waveforms.First,data collected by MMS was generated into 6-channel original waveforms based on events.After that,sample data sets of microseismic events,blasts,drillings,and noises were established through manual identification.These datasets were split into training sets and test sets according to a certain proportion,and transfer learning was performed on AlexNet,GoogLeNet,and ResNet50 pre-training network models,respectively.After training and tuning,optimal models were retained and compared with support vector machine classification.Results show that transfer learning models perform well on different test sets.Overall,GoogLeNet performed best,with a recognition accuracy of 99.8%.Finally,the possible effects of the number of training sets and the imbalance of different types of sample data on the accuracy and effectiveness of classification models were discussed.

A 3D microseismic data-driven damage model for jointed rock mass under hydro-mechanical coupling conditions and its application

Rock mass is a fractured porous medium usually subjected to complex geostress and fluid pressure simultaneously.Moreover,the properties of rock mass change in time and space due to mining-induced fractures.Therefore,it is always challenging to accurately measure rock mass properties.In this study,a three-dimensional(3D)microseismic(MS)data-driven damage model for jointed rock mass under hydro-mechanical coupling conditions is proposed.It is a 3D finite element model that takes seepage,damage and stress field effects into account jointly.Multiple factors(i.e.joints,water and microseismicity)are used to optimize the rock mass mechanical parameters at different scales.The model is applied in Shirengou iron mine to study the damage evolution of rock mass and assess the crown pillar stability during the transition from open-pit to underground mining.It is found that the damage pattern is mostly controlled by the structure,water and rock mass parameters.The damage pattern is evidently different from the two-dimensional result and is more consistent with the field observations.This difference is caused by the MS-derived damage acting on the rock mass.MS data are responsible for gradually correcting the damage zone,changing the direction in which it expands,and promoting it to evolve close to reality.For the crown pillar,the proposed model yields a more trustworthy safety factor.In order to guarantee the stability of the pillar,it is suggested to take waterproof and reinforcement measures in areas with a high degree of damage.

Comprehensive early warning of rock burst utilizing microseismic multi-parameter indices

Rock bursts have become one of the most severe risks in underground coal mining and its early warning is an important component in the safety management. Microseismic(MS) monitoring is considered potentially as a powerful tool for the early warning of rock burst. In this study, an MS multi-parameter index system was established and the critical values of each index were estimated based on the normalized multi-information warning model of coal-rock dynamic failure. This index system includes bursting strain energy(BSE) index, time-space-magnitude independent information(TSMII) indices and timespace-magnitude compound information(TSMCI) indices. On the basis of this multi-parameter index system, a comprehensive analysis was conducted via introducing the R-value scoring method to calculate the weights of each index. To calibrate the multi-parameter index system and the associated comprehensive analysis, the weights of each index were first confirmed using historical MS data occurred in LW402102 of Hujiahe Coal Mine(China) over a period of four months. This calibrated comprehensive analysis of MS multi-parameter index system was then applied to pre-warn the occurrence of a subsequent rock burst incident in LW 402103. The results demonstrate that this multi-parameter index system combined with the comprehensive analysis are capable of quantitatively pre-warning rock burst risk.

Numerical simulation of hydraulic fracturing and associated microseismicity using finite-discrete element method

Hydraulic fracturing(HF) technique has been extensively used for the exploitation of unconventional oil and gas reservoirs. HF enhances the connectivity of less permeable oil and gas-bearing rock formations by fluid injection, which creates an interconnected fracture network and increases the hydrocarbon production. Meanwhile, microseismic(MS) monitoring is one of the most effective approaches to evaluate such stimulation process. In this paper, the combined finite-discrete element method(FDEM) is adopted to numerically simulate HF and associated MS. Several post-processing tools, including frequency-magnitude distribution(b-value), fractal dimension(D-value), and seismic events clustering,are utilized to interpret numerical results. A non-parametric clustering algorithm designed specifically for FDEM is used to reduce the mesh dependency and extract more realistic seismic information.Simulation results indicated that at the local scale, the HF process tends to propagate following the rock mass discontinuities; while at the reservoir scale, it tends to develop in the direction parallel to the maximum in-situ stress.

Propagation patterns of microseismic waves in rock strata during mining:an experimental study

Microseismic monitoring has been widely used in mines for monitoring and predicting dynamic disasters such as rockbursts and waterbursts. However, to develop high-precision microseismic monitoring systems, the propagation patterns of microseismic waves under complex geological conditions must be elucidated. To achieve this aim, a simulation model of a typical coalmine was designed using similar materials according to the similarity theory to simulate the mining process. Geophones were embedded into the model to detect the propagation of elastic waves from microseisms. The results show that in an unmined solid rock mass, the wave velocity in shallow rock strata is mainly affected by geologically weak planes, whereas in deep strata it is affected mainly by the density of the rock mass. During propagation, the amplitude first decreases and then increases rapidly with increasing propagation distance from the coal layer. After mining, our results indicate that the goaf causes significant attenuation of the wave velocity. After the goaf was backfilled, the velocity attenuation is reduced to some extent but not eliminated. The results of this study can be used as guidelines for designing and applying microseismic monitoring systems in mines.

Fast Marching Method for Microseismic Source Location in Cavern-Containing Rockmass: Performance Analysis and Engineering Application

Microseismic(MS)event locations are vital aspect of MS monitoring technology used to delineate the damage zone inside the surrounding rock mass.However,complex geological conditions can impose significantly adverse effects on the final location results.To achieve a high-accuracy location in a complex cavern-containing structure,this study develops an MS location method using the fast marching method(FMM)with a second-order difference approach(FMM2).Based on the established velocity model with three-dimensional(3D)discrete grids,the realization of the MS location can be achieved by searching the minimum residual between the theoretical and actual first arrival times.Moreover,based on the calculation results of FMM2,the propagation paths from the MS sources to MS sensors can be obtained using the linear interpolation approach and the Runge–Kutta method.These methods were validated through a series of numerical experiments.In addition,our proposed method was applied to locate the recorded blasting and MS events that occurred during the excavation period of the underground caverns at the Houziyan hydropower station.The location results of the blasting activities show that our method can effectively reduce the location error compared with the results based on the uniform velocity model.Furthermore,the obtained MS location was verified through the occurrence of shotcrete fractures and spalling,and the monitoring results of the in-situ multipoint extensometer.Our proposed method can offer a more accurate rock fracture location and facilitate the delineation of damage zones inside the surrounding rock mass.

Identification methods for anomalous stress region in coal roadways based on microseismic information and numerical simulation

It is believed that the microseismicity induced by mining effect and gas gradient disturbance stress is a precursor to the essential characteristics of roadway unstability. In order to effectively identify and evaluate the stability of coal roadways in the process of mine development and extraction, a microseismic monitoring system was deployed for the study of the stress evolution process, damage degree and distribution characteristics in the tailgate and headgate. The mine under study is the 62113 outburst working face of Xin Zhuangzi coalmine in Huainan mining area. The whole process of microfractures initiation,extension, interaction and coalescence mechanisms during the progressive failure processes of the coal rock within the delineated and typical event clusters were investigated by means of a two dimensional realistic failure process analysis code(RFPA2D-Flow). The results show that the microseismic events gradually create different-sized event clusters. The microseismicity of the tailgate is significantly higher than that of the headgate. The study indicates that the greater anomalous stress region matches the area where microfractures continuously develop and finally connect to each other and form a fissure zone.Due to the mine layout and stress concentration, the ruptured area is mainly located on the left shoulder of the tailgate roof. The potential anomalous stress region of the coal roadway obtained by numerical simulation is relatively in good agreement with the trend of spatial macro evolution of coal rock microfractures captured by the microseismic monitoring system. The research results can provide important basis for understanding instability failure mechanism of deep roadway and microseismic activity law in complex geologic conditions, and it ultimately can be used to guide the selection and optimization of reinforcement and protection scheme.

Activation characteristics analysis on concealed fault in the excavating coal roadway based on microseismic monitoring technique

In order to effectively monitor the concealed fault activation process in excavation activities, based on the actual condition of a working face containing faults with high outburst danger in Xin Zhuangzi mine in Huainan, China, we carried out all-side tracking and monitoring on the fault activation process and development trend in excavation activities by establishing a microseismic monitoring system. The results show that excavation activities have a rather great influence on the fault activation. With the working face approaching the fault, the fault activation builds up and the outburst danger increases; when the excavation activities finishes, the fault activation tends to be stable. The number of microseismic events are corresponding to the intensity of fault activation, and the distribution rules of microseismic events can effectively determine the fault occurrence in the mine. Microseismic monitoring technique is accurate in terms of detecting geologic tectonic activities, such as fault activations lying ahead during excavation activities. By utilizing this technique, we can determine outburst danger in excavation activities in time and accordingly take effective countermeasures to prevent and reduce the occurrence of outburst accidents.

Time-reverse location of microseismic sources in viscoelastic orthotropic anisotropic medium based on attenuation compensation

Time reversal is a key component of time-reverse migration and source location using wavefield extrapolation.The implementation of time reversal depends on the time symmetry of wave equations in acoustic and elastic media.This symmetry in time is no longer valid in attenuative medium.Not only the velocity is anisotropic in shale oil and gas reservoirs,but also the attenuation is usually anisotropic,which can be characterized by viscoelastic orthotropic media.In this paper,the fractional order viscoelastic anisotropic wave equation is used to decouple the energy dissipation and the velocity dispersion.By changing the sign of the dissipation term during backpropagation,the anisotropic attenuation is compensated and the time symmetry is restored.The attenuation compensation time-reverse location algorithm can eff ectively locate the source in viscoelastic orthotropic media.Compared to cases without attenuation compensation or using isotropic attenuation compensation,this method can remove location error caused by anisotropic attenuation and improve the imaging eff ect of the source.This paper verifi es the eff ectiveness of the method through theoretical analysis and model testing.

Model test and numerical simulation on the dynamic stability of the bedding rock slope under frequent microseisms

Shake table testing was performed to investigate the dynamic stability of a mid-dip bedding rock slope under frequent earthquakes. Then, numerical modelling was established to further study the slope dynamic stability under purely microseisms and the influence of five factors, including seismic amplitude, slope height, slope angle, strata inclination and strata thickness, were considered. The experimental results show that the natural frequency of the slope decreases and damping ratio increases as the earthquake loading times increase. The dynamic strength reduction method is adopted for the stability evaluation of the bedding rock slope in numerical simulation, and the slope stability decreases with the increase of seismic amplitude, increase of slope height, reduction of strata thickness and increase of slope angle. The failure mode of a mid-dip bedding rock slope in the shaking table test is integral slipping along the bedding surface with dipping tensile cracks at the slope rear edge going through the bedding surfaces. In the numerical simulation, the long-term stability of a mid-dip bedding slope is worst under frequent microseisms and the slope is at risk of integral sliding instability, whereas the slope rock mass is more broken than shown in the shaking table test. The research results are of practical significance to better understand the formation mechanism of reservoir landslides and prevent future landslide disasters.

Microseismic monitoring and numerical simulation on the stability of high-steep rock slopes in hydropower engineering

For high-steep slopes in hydropower engineering, damage can be induced or accumulated due to a series of human or natural activities, including excavation, dam construction, earthquake, rainstorm, rapid rise or drop of water level in the service lifetime of slopes. According to the concept that the progressive damage(microseismicity) of rock slope is the essence of the precursor of slope instability, a microseismic monitoring system for high-steep rock slopes is established. Positioning accuracy of the monitoring system is tested by fixed-position blasting method. Based on waveform and cluster analyses of microseismic events recorded during test, the tempo-spatial distribution of microseismic events is analyzed.The deformation zone in the deep rock masses induced by the microseismic events is preliminarily delimited. Based on the physical information measured by in situ microseismic monitoring, an evaluation method for the dynamic stability of rock slopes is proposed and preliminarily implemented by combining microseismic monitoring and numerical modeling. Based on the rock mass damage model obtained by back analysis of microseismic information, the rock mass elements within the microseismic damage zone are automatically searched by finite element program. Then the stiffness and strength reductions are performed on these damaged elements accordingly. Attempts are made to establish the correlation between microseismic event, strength deterioration and slope dynamic instability, so as to quantitatively evaluate the dynamic stability of slope. The case studies about two practical slopes indicate that the proposed method can reflect the factor of safety of rock slope more objectively. Numerical analysis can help to understand the characteristics and modes of the monitored microseismic events in rock slopes. Microseismic monitoring data and simulation results can be used to mutually modify the sensitive rock parameters and calibrate the model. Combination of microseismic monitoring and numerical simulation provides a more objective basis for the numerical model and parameters and a solid mechanical foundation for the microseismic monitoring.

Downhole Microseismic Source Location Based on a Multi-Dimensional DIRECT Algorithm for Unconventional Oil and Gas Reservoir Exploration

Downhole microseismic data has the significant advantages of high signal-to-noise ratio and well-developed P and S waves and the core component of microseismic monitoring is microseismic event location associated with hydraulic fracturing in a relatively high confidence level and accuracy.In this study,we present a multidimensional DIRECT inversion method for microseismic locations and applicability tests over modeling data based on a downhole microseismic monitoring system.Synthetic tests inidcate that the objective function of locations can be defined as a multi-dimensional matrix space by employing the global optimization DIRECT algorithm,because it can be run without the initial value and objective function derivation,and the discretely scattered objective points lead to an expeditious contraction of objective functions in each dimension.This study shows that the DIRECT algorithm can be extensively applied in real downhole microseismic monitoring data from hydraulic fracturing completions.Therefore,the methodology,based on a multidimensional DIRECT algorithm,can provide significant high accuracy and convergent efficiency as well as robust computation for interpretable spatiotemporal microseismic evolution,which is more suitable for real-time processing of a large amount of downhole microseismic monitoring data.

Microseismic Imaging of Hydraulically Induced-Fractures in Gas Reservoirs: A Case Study in Barnett Shale Gas Reservoir, Texas, USA

Microseismic technology has been proven to be a practical approach for in-situ monitoring of fracture growth during hydraulic fracture stimulations. Microseismic monitoring has rapidly evolved in acquisition methodology, data processing, and in this paper, we evaluate the progression of this technology with emphasis on their applications in Barnett shale gas reservoir. Microseismic data analysis indicates a direct proportion between microseismic moment magnitude and depth, yet no relation between microseismic activity and either injection rate or injection volume has been observed. However, large microseismic magnitudes have been recorded where hydraulic fracturing stimulation approaches a fault and therefore the geologic framework should be integrated in such programs. In addition, the geometry of fracture growth resulted by proppant interactions with naturally fractured formations follows unpredictable fashion due to redirecting the injection fluids along flow paths associated with the pre-existing fault network in the reservoir. While microseismic imaging is incredibly useful in revealing the fracture geometry and the way the fracture evolves, recently several concerns have been raised regarding the capability of microseismic data to provide the fracture dimensional parameters and the fracture mechanism that could provide detailed information for reservoir characterization.

An improved empirical green function method to extract microseismic signals

In mining, reservoir impoundment and hydraulic fracturing exploitation, the induced microseismic clusters may present complex waveforms at receivers since the individual events generally arrive very close. And the routine methods for arrival picking are insufficiently efficient due to these strong influences. Here, we modified the empirical green function method and applied it to extract the green functions and the radiation coefficients of microseismic events with the largest energy in clusters.Multiple-channel records were used to estimate an "average" source spectrum and then the "average" source wavelet was removed from the records by deconvolution. We applied this method to the real data,and the result indicated clear improvement in extracting the dominant event of the clusters.

Stability evaluation for steep bank slope with microseismic monitoring in Three Gorges Reservoir area

Rock slide is one of the common geohazard in the Three Gorges Reservoir area, and it affects the shipping of the Yangtze River and the safety of people living on the banks. In order to investigate the internal fracturing mechanism of rock mass, distributed microseismic monitoring network was arranged with 15 three component geophones(3C geophones), deployed at borehole and out of the sliding mass in the unstable Dulong slope. Stein Unbiased Risk Estimation(SURE) method was used to noise suppression for the microseismic record, and decomposition parameters of the Continuous Wavelet Transform(CWT) were determined with maximum energy of correlation coefficient(MECC) method. The signal-to-noise ratio was tripled after the process, and source parameters are obtained with full waveform inversion. The rupture volume model was counted by the irregular grid statistics with the events’ density. It shows that the rock slide is of a small scale and composed of a single block. Moreover, the relationship among microseismicity, displacement and rainfall were discussed in the paper. The deformation rate was dramatically changed in the period of intensive events. There is a good consistency especially in the rainfall period. Although there is a time delay, continuous rainfall is more likely to cause the increase of microseismic events. The results show that the Dulong slope is a shallow rock slide in the state of creep deformation, and the rupture mechanism of the rock mass is left-lateral normal fault with shear failure. The research provides more key information for the early warning and prevention of rock slides and helps to reduce the risk of geohazards.

Master event based backazimuth estimation and its application to downhole microseismic monitoring

Microseismic monitoring provides a valuable tool for evaluating the effectiveness of hydraulic fracturing operations.However,robust detection and accurate location of microseismic events are challenging due to the low signal to noise ratio(SNR)of their signals on seismograms.In a downhole monitoring setting,P-wave polarization direction measured from 3-component records is usually considered as the backazimuth of the microseismic event,i.e.,the direction of the event.The direction and arrival time difference between the P and S waves is used to locate the seismic event.When SNR is low,an accurate estimate of event backazimuth becomes very challenging with the traditional covariance matrix method.Here we propose to employ a master event and use a grid search method to find the backazimuth of a target event that maximizes the dot product of the two backazimuthal vectors of the master and target events.We compared the backazimuths measured with the proposed grid-search and the conventional covariance-matrix methods using a large synthetic dataset.We found that the grid-search method yields more accurate backazimuth estimates from low SNR records when measurements are made at single geophone level.When array data are combined,the proposed method also has some advantage over the covariance-matrix method,especially when the number of geophones is low.We also applied the method to a microseismic dataset acquired by a hydraulic fracturing project at a shale play site in southwestern China and found that the relocated microseismic events tend to align along existing faults more tightly than those in the original catalog.