Abstract
This paper considers the possibilities of using artificial neural networks (ANN) for seismic monitoring, which pertains to the problem of detecting and recognizing seismic events, followed by assessment of the nature and causes of their occurrence. This problem is not always solved efficiently by known analytical and numerical modeling methods. Therefore, the author considered the possibility of using an ANN for its solution. This approach induces certain interest in the scientific literature, and a number of publications are devoted to it. In this paper, the author has attempted from his own positions to generalize and systematize the basic information about neural networks, their structure, and principles of operation. The article presents processing by neural networks. A layer was taken as the basic unit of the ANN, which simplifies understanding of the structure and operating principles of ANN and can be especially useful when solving the applied problems. The applied part of the paper is devoted to the features of neural networks used in seismic monitoring tasks. The main data types characteristic of seismic monitoring tasks are given. The peculiarities of their use in neural networks are considered. The final part of the paper gives an example of practical use of a neural network for detecting false seismic events. On the basis of the perceptron, the neural classifier was constructed, which was used to search for false positives yielded by a weak seismic event detector. The total accuracy of the detector was found to be 88%. Thus, the paper shows with a practical example that, despite the comparative simplicity of an ANN device, they can still solve complex seismic monitoring tasks while significantly saving time and man-hours in preparing and processing seismic data.
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.