Deep Neural Network for Real-Time Location and Moment Tensor Inversionof Borehole Microseismic Events Induced by Hydraulic Fracturing

摘要

Locations and source mechanisms of microseismic events are very crucial for understanding the fracturingbehavior and evolution of stress fields within the reservoir and hence facilitates the detection of hydraulicfracture growth and estimation of the stimulated reservoir volume(SRV).In the classic workflow,thereare two main methods for locating microseismic events with a calibrated fixed velocity model:grid searchand linear inversion.The grid search is very stable;can find a global minimum and does not need initialevent locations.However,it is computationally intensive and its resolution depends on the grid size,hence,it is not suitable for real-time monitoring.On the other hand,although the linear inversion method is quitefast,the inversion may be pushed into a local minimum by thin shale layers and large velocity contrastsleading to false locations.The source mechanisms of the located events,which provide information aboutthe magnitudes,modes and orientations of the fractures,are obtained through moment tensor inversionof the recorded waveforms.In this paper,we propose a deep neural network approach to solve theabove challenges,in real-time,and increase the efficiency and accuracy of location and moment tensorinversion of microseismic events,induced during hydraulic fracturing.Location of microseismic events wasconsidered as a multi-dimensional and non-linear regression problem and a multi-layer two-dimensional(2D)convolutional neural network(CNN)was designed to perform the inversion.The source mechanismsof the microseismic events were inverted using a multi-head one-dimensional(1D)CNN.The neuralnetworks were trained using synthetic microseismic events with low signal to noise ratio(SNR)to imitatefield data.The overall results indicate that both the 2D CNN and 1D CNN models are capable of learningthe relationship between the events locations and source mechanisms and the waveform data to a highdegree of precision compared to classical methods.Both the event location and source mechanism errors areless than few percent.Deep learning offers a number of benefits for automated and real-time microseismicevent location and moment tensor inversion,including least preprocessing,continuous improvement inperformance as more training data is obtained,as well as low computational cost.