A Dual-Task Approach for Onset Time Picking and the Detection of Microseismic Waveforms Based on Deep Learning

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.