Integrated processing method for microseismic signal based on deep neural network

Abstract

Summary Denoising and onset time picking of signals are essential before extracting source information from collected seismic/microseismic data. We proposed an advanced deep dual-tasking network (DDTN) that integrates these two procedures sequentially to achieve the optimal performance. Two homo-structured encoder-decoder networks with specially designed structures and parameters are connected in series for handling the denoising and detection of microseismic signals. Based on the similarity of data types, the output of the denoising network will be imported into the detection network to obtain labels for the signal duration. The procedures of denoising and duration detection can be completed in an integrated way, where the denoised signals can improve the accuracy of onset time picking. Results show that the method has a good performance for the denoising of microseismic signals that contain various types and intensities of noise. Compared with existing methods, DDTN removes the noise with a minor waveform distortion. It is ideal for recovering the microseismic signal while maintaining a good capacity for onset time picking when the signal-to-noise ratio is low. Based on that, the second network can detect a more accurate duration of microseismic signals and thus obtain more accurate onset time. The method has great potential to be extended to the study of exploration seismology and earthquakes.

Classification of Microseismic Signals Using Machine Learning

“…It involves the use of acoustic-electric sensors to monitor the generation of elastic waves during the rock mass failure process, thereby obtaining spatiotemporal strength information related to microseismic events and facilitating the prediction of mining-induced dynamic disasters [5][6][7][8]. Before predicting mining-induced dynamic disasters, a series of preprocessing steps are required for microseismic signals: microseismic signal classification [9][10][11][12][13], microseismic signal denoising [14,15], initial arrival time picking [16,17], and seismic source localization [18][19][20]. Microseismic signal classification represents the first step in the preprocessing of microseismic signals and is a crucial component to ensure the effectiveness of subsequent procedures.…”

Convolutional neural network‐based classification of microseismic events originating in a stimulated reservoir from distributed acoustic sensing data

“…In the context of hydraulic stimulation monitoring, CNNs have been used to detect microseismic events recorded by both surface arrays (Consolvo & Thornton, 2020) and downhole DAS (Binder & Tura, 2020;Stork et al, 2020;Huot et al, 2021). In order to process and denoise microseismic data, convolutional encoder-decoder networks , deep dualtasking networks (Zhang et al, 2021) and unsupervised learning for signal feature extraction (Zhang & van der Baan, 2020) have all been successfully implemented. Machine learning algorithms are also useful for automatically detecting signals recorded by fibre optics in the near surface.…”