West Texas has been a seismically active region in the past decade due to the injection of industrial wastewater and hydrocarbon exploitation. The newly founded Texas seismological network has provided a catalog that characterizes the intense seismicity down to a magnitude of 1.5 Ml. However, analyzing numerous small-magnitude events (Ml< 1.0) is prohibitively unaffordable. We propose to apply an advanced deep learning method, the earthquake compact convolutional transformer (EQCCT), to relieve the workload of analyzing thousands of small earthquakes per month in West Texas. The EQCCT method is embedded in an integrated detection and location framework to seamlessly output a highly complete earthquake catalog. The EQCCT enables us to detect and locate 50 times more earthquakes than previously possible. We apply the EQCCT-embedded detection and location workflow to the Culberson and Mentone Earthquake Zone (CMEZ) in West Texas. Association with nearby injection activities reveals an intricate correlation between the rate of injected fluid volume and the number of small earthquakes.

Keywords:
plate tectonics, geologist, artificial intelligence, catalog, savvaidis, applied geoscience & energy 10, injection, american association, deep learning, reservoir characterization
Subjects:
Reservoir Characterization, Information Management and Systems, Seismic processing and interpretation, Artificial intelligence, Neural networks
This content is only available via PDF.
Copyright 2024, Society of Exploration Geophysicists and the American Association of Petroleum Geologists
You can access this article if you purchase or spend a download.