Abstract
Passive seismic experiments have been proposed as a cost-effective and non-invasive alternative to controlled-source seismology, allowing body–wave reflections based on seismic interferometry principles to be retrieved. However, from the huge volume of the recorded ambient noise, only selected time periods (noise panels) are contributing constructively to the retrieval of reflections. We address the issue of automatic scanning of ambient noise data recorded by a large-N array in search of body–wave energy (body–wave events) utilizing a convolutional neural network (CNN). It consists of computing first both amplitude and frequency attribute values at each receiver station for all divided portions of the recorded signal (noise panels). The created 2-D attribute maps are then converted to images and used to extract spatial and temporal patterns associated with the body–wave energy present in the data to build binary CNN-based classifiers. The ensemble of two multi-headed CNN models trained separately on the frequency and amplitude attribute maps demonstrates better generalization ability than each of its participating networks. We also compare the prediction performance of our deep learning (DL) framework with a conventional machine learning (ML) algorithm called XGBoost. The DL-based solution applied to 240 h of ambient seismic noise data recorded by the Kylylahti array in Finland demonstrates high detection accuracy and the superiority over the ML-based one. The ensemble of CNN-based models managed to find almost three times more verified body–wave events in the full unlabelled dataset than it was provided at the training stage. Moreover, the high-level abstraction features extracted at the deeper convolution layers can be used to perform unsupervised clustering of the classified panels with respect to their visual characteristics.
Highlights
We provide the summary statistics of the overall prediction results achieved with the ensemble of convolutional neural network (CNN)-based models and present the outcome of the unsupervised deep embedded clustering that aims to categorize the detected noise panels
We have developed a deep learning technique for automatic data selection in massive ambient noise datasets recorded by a dense receiver array
It is designed to detect and isolate the time periods dominated by the body–wave energy based on the spatio-temporal characteristics of the signals that propagate across the seismic network
Summary
It is possible to mimic, to some extent, controlled-source seismic data at the site where a passive seismic experiment is carried out by applying seismic interferometry (SI) to ambient noise recordings [1]. As long as the wavefield is diffuse, ambient noise SI (ANSI) allows the impulse response of a medium to be extracted from the noise recorded at two receivers based on their averaged cross-correlation as if one of them was a source [2,3,4]. SI by cross-correlation, as an alternative to active-source reflection seismic surveys, has been successfully applied in numerous studies ranging from subsurface imaging [5,6,7,8,9,10,11,12] for monitoring purposes [13,14]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.