scholarly journals Seismic Monitoring in Zhezkazgan Mines - Case Study of a Strong Seismic Event Forecasting

Author(s):  
Victor German ◽  
Vladimir Mansurov ◽  
P Boiko
2020 ◽  
Vol 92 (1) ◽  
pp. 388-395
Author(s):  
Lisa Linville ◽  
Dylan Anderson ◽  
Joshua Michalenko ◽  
Jennifer Galasso ◽  
Timothy Draelos

Abstract The impressive performance that deep neural networks demonstrate on a range of seismic monitoring tasks depends largely on the availability of event catalogs that have been manually curated over many years or decades. However, the quality, duration, and availability of seismic event catalogs vary significantly across the range of monitoring operations, regions, and objectives. Semisupervised learning (SSL) enables learning from both labeled and unlabeled data and provides a framework to leverage the abundance of unreviewed seismic data for training deep neural networks on a variety of target tasks. We apply two SSL algorithms (mean-teacher and virtual adversarial training) as well as a novel hybrid technique (exponential average adversarial training) to seismic event classification to examine how unlabeled data with SSL can enhance model performance. In general, we find that SSL can perform as well as supervised learning with fewer labels. We also observe in some scenarios that almost half of the benefits of SSL are the result of the meaningful regularization enforced through SSL techniques and may not be attributable to unlabeled data directly. Lastly, the benefits from unlabeled data scale with the difficulty of the predictive task when we evaluate the use of unlabeled data to characterize sources in new geographic regions. In geographic areas where supervised model performance is low, SSL significantly increases the accuracy of source-type classification using unlabeled data.


Author(s):  
Cécile Berron ◽  
Laurène Michou ◽  
Benoit De Cacqueray ◽  
Florian Duret ◽  
Julien Cotton ◽  
...  

2016 ◽  
Vol 49 ◽  
pp. 201-216 ◽  
Author(s):  
Stas Glubokovskikh ◽  
Roman Pevzner ◽  
Tess Dance ◽  
Eva Caspari ◽  
Dmitry Popik ◽  
...  
Keyword(s):  

2018 ◽  
Vol 66 ◽  
pp. 01010
Author(s):  
Anna Barbara Gogolewska ◽  
Natalia Czajkowska

The copper ore deposit situated in the south-west of Poland is mined by three underground mines owned by KGHM Polish Copper JSC. Exploitation has been accompanied by rock burst hazard since the beginning. Thus, numerous different preventing measures have been developed such as temporary, organizational and long-term ones. However, no one has been able to predict the time, place and energy of a seismic event. The group winning blasting, with maximum number of blasted faces, is the most effective operation to reduce seismic threat. The more faces are blasted the more seismic energy should be reduced. The study aims at assessing the blasting effectiveness in inducing rock bursts and tremors. For this purpose, the seismic activity induced by mining and blasting were investigated. The number of blasting works and blasted faces as well as length of time between subsequent blasting works were analysed and related to provocation effectiveness. The linear correlation and different regressions were calculated to determine these relations. Moreover, the seismic energy reduction in the rock mass was evaluated by means of SRMS Index, which is a factor measured directly before and after blasting. The analyses covered one mine panel in the Polkowice-Sieroszowice copper mine over four-year period.


2020 ◽  
Author(s):  
Denis Kiyashchenko ◽  
Wai-Fan Wong ◽  
Dalila Cherief ◽  
Dan Clarke ◽  
Yuting Duan ◽  
...  
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document