Three-Component Microseismic Data Denoising Based on Re-Constrain Variational Mode Decomposition

Microseismic monitoring is an important technology used to evaluate hydraulic fracturing, and denoising is a crucial processing step. Analyses of the characteristics of acquired three-component microseismic data have indicated that the vertical component has a higher signal-to-noise ratio (SNR) than the two horizontal components. Therefore, we propose a new denoising method for three-component microseismic data using re-constrain variational mode decomposition (VMD). In this method, it is assumed that there is a linear relationship between the modes with the same center frequency among the VMD results of the three-component data. Then, the decomposition result of the vertical component is used as a constraint to the whole denoising effect of the three-component data. On the basis of VMD, we add a constraint condition to form the re-constrain VMD, and deduce the corresponding solution process. According to the synthesis data analysis, the proposed method can not only improve the SNR level of three-component records, it also improves the accuracy of polarization analysis. The proposed method also achieved a satisfactory effect for field data.

Arrival-time picking of microseismic events based on MSNet

Arrival-time picking of microseismic events is a critical procedure in microseismic data processing. However, as field monitoring data contain many microseismic events with low signal-to-noise ratios (SNRs), traditional arrival-time picking methods based on the instantaneous characteristics of seismic signals cannot meet the picking accuracy and efficiency requirements of microseismic monitoring owing to the large volume of monitoring data. Conversely, methods based on deep neural networks can significantly improve arrival-time picking accuracy and efficiency in low-SNR environments. Therefore, we propose a deep convolutional network that combines the U-net and DenseNet approaches to pick arrival times automatically. This novel network, called MSNet not only retains the spatial information of any input signal or profile based on the U-net, but also extracts and integrates more essential features of events and non-events through dense blocks, thereby further improving the picking accuracy and efficiency. An effective workflow is developed to verify the superiority of the proposed method. First, we describe the structure of MSNet and the workflow of the proposed picking method. Then, datasets are constructed using variable microseismic traces from field microseismic monitoring records and from the finite-difference forward modeling of microseismic data to train the network. Subsequently, hyperparameter tuning is conducted to optimize the MSNet. Finally, we test the MSNet using modeled signals with different SNRs and field microseismic data from different monitoring areas. By comparing the picking results of the proposed method with the results of U-net and short-term average and long-term average (STA/LTA) methods, the effectiveness of the proposed method is verified. The arrival picking results of synthetic data and microseismic field data show that the proposed network has increased adaptability and can achieve high accuracy for picking the arrival-time of microseismic events.

Multi-Classification of Complex Microseismic Waveforms Using Convolutional Neural Network: A Case Study in Tunnel Engineering

Due to the complexity of the various waveforms of microseismic data, there are high requirements on the automatic multi-classification of such data; an accurate classification is conducive for further signal processing and stability analysis of surrounding rock masses. In this study, a microseismic multi-classification (MMC) model is proposed based on the short time Fourier transform (STFT) technology and convolutional neural network (CNN). The real and imaginary parts of the coefficients of microseismic data are inputted to the proposed model to generate three classes of targets. Compared with existing methods, the MMC has an optimal performance in multi-classification of microseismic data in terms of Precision, Recall, and F1-score, even when the waveform of a microseismic signal is similar to that of some special noise. Moreover, semisynthetic data constructed by clean microseismic data and noise are used to prove the low sensitivity of the MMC to noise. Microseismic data recorded under different geological conditions are also tested to prove the generality of the model, and a microseismic signal with Mw ≥ 0.2 can be detected with a high accuracy. The proposed method has great potential to be extended to the study of exploration seismology and earthquakes.

Deep Neural Networks for Detection and Location of Microseismic Events and Velocity Model Inversion from Microseismic Data Acquired by Distributed Acoustic Sensing Array

Fiber-optic cables have recently gained popularity for use as Distributed Acoustic Sensing (DAS) arrays for borehole microseismic monitoring due to their physical robustness as well as high spatial and temporal resolutions. As a result, the sensors record large amounts of data, making it very difficult to process in real-/semi-real-time using the conventional processing routines. We present a novel approach, based on deep learning, for handling the large amounts of DAS data in real-/semi-real-time. The proposed neural network was trained on synthetic microseismic data contaminated with real-ambient noise from field data and was validated using field DAS microseismic data obtained from a hydraulic fracturing operation. The results indicate that the trained network is capable of detecting and locating microseismic events from DAS data and simultaneously update the velocity model to a high degree of precision. The mean absolute errors in the event locations and the velocity model parameters are 2.04, 0.72, 2.76, 4.19 and 0.97 percent for distance (x), depth (z), P-wave velocity, S-wave velocity and density, respectively. In addition to automation and computational efficiency, deep learning reduces human expert data handling during processing, thus preserving data integrity leading to more accurate and reproducible results.

Predicting the azimuth of natural fractures and in-situ horizontal stress: A case study from Sichuan Basin, China

The azimuth of fractures and in-situ horizontal stress are important factors in planning horizontal wells and hydraulic fracturing for unconventional resources plays. The azimuth of natural fractures can be directly obtained by analyzing image logs. The azimuth of the maximum horizontal stress σH can be predicted by analyzing the induced fractures on image logs. The clustering of micro-seismic events can also be used to predict the azimuth of in-situ maximum horizontal stress. However, the azimuth of natural fractures and the in-situ maximum horizontal stress obtained from both image logs and micro-seismic events are limited to the wellbore locations. Wide azimuth seismic data provides an alternative way to predict the azimuth of natural fractures and maximum in-situ horizontal stress if the seismic attributes are properly calibrated with interpretations from well logs and microseismic data. To predict the azimuth of natural fractures and in-situ maximum horizontal stress, we focus our analysis on correlating the seismic attributes computed from pre-stack and post-stack seismic data with the interpreted azimuth obtained from image logs and microseismic data. The application indicates that the strike of the most positive principal curvature k1 can be used as an indicator for the azimuth of natural fractures within our study area. The azimuthal anisotropy of the dominant frequency component if offset vector title (OVT) seismic data can be used to predict the azimuth of maximum in-situ horizontal stress within our study area that is located the southern region of the Sichuan Basin, China. The predicted azimuths provide important information for the following well planning and hydraulic fracturing.

An Efficient Hydraulic Fracture Geometry Calibration Workflow Using Microseismic Data, Geomechanics, DFN Models, and History Matching

Reliable estimates of hydraulic fracture geometry help reduce the uncertainty associated with estimated ultimate recovery (EUR) forecasts and optimize field developing planning in unconventional reservoirs. For these reasons, operators gather information from different sources with the objective to calibrate their hydraulic fracture models. Microseismic data is commonly acquired by operators to estimate hydraulic fracture geometry and to optimize well completion designs. However, relying solely on estimates derived from microseismic information may lead to inaccurate estimates of hydraulic fracture geometry. The objective of this study is to efficiently calibrate hydraulic fracture geometry by using microseismic data, physics-based fracture propagation models, and the embedded discrete fracture model (EDFM). We first obtain preliminary estimates of fracture geometry based on microseismic events’ spatial location and density with respect to the perforation cluster location. We then tune key completion parameters using an in-house fracture propagation model to provide hydraulic fracture geometries that are constrained by the microseismic cloud. In the history matching process, we included the effect of natural fractures, using the microseismic events location as natural fracture initiation points. Finally, we used cutoff coefficients to further reduce hydraulic fracture geometries to match production data. The results of this work showed a fast and flexible method to estimate fracture half-lengths and fracture heights, resulting in a direct indicator of the completion design. Additionally, hydraulic-natural fracture interactions were assessed. We concluded that the inclusion of cutoff coefficients as history matching parameters allows to derive realistic hydraulic and natural fracture models calibrated with microseismic and production data in unconventional reservoirs.