Title:
Human and Machine Listening of Seismic Data

Thumbnail Image
Files
ICAD2017_paper_47.pdf (1.03 MB)
Author(s)
Paté, Arthur
 Holtzman, Benjamin
 Waldhauser, Felix
 Repetto, Douglas
 Paisley, John
Authors
Advisor(s)
Advisor(s)
Editor(s)
Associated Organization(s)
Organizational Unit
Series
Collections
Scholarly Events
Supplementary to
Permanent Link
http://hdl.handle.net/1853/58368
Abstract
Geothermal energy mining consists of injecting cold water into hot rocks in order to create micro-fractures allowing heat to be extracted and converted into electrical energy. This water injection can trigger several rock fracture processes. Seismologists are facing the challenge of identifying and understanding these fracture processes in order to maximize heat extraction and minimize induced seismicity. Our assumption is that each fracture process is characterized by spectro-temporal features and patterns that are not picked up by current signal processing methods used in seismology, but can be identified by the human auditory system and/or by machine learning. We present here a pluridisciplinary methodology aimed at addressing this problem, combining machine learning, auditory display and sound perception.
Sponsor
Date Issued
2017-06
Extent
Resource Type
Text
Resource Subtype
Proceedings
Rights Statement
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Rights URI
http://creativecommons.org/licenses/by-nc/4.0/