\textsc{DeFault}: Deep-learning-based Fault Delineation
Authors:
- Hanchen WangHWHanchen Wang
- Yinpeng ChenYCYinpeng Chen
- Tariq AlkhalifahTATariq Alkhalifah
- Ting ChenTCTing Chen
- Youzuo LinYLYouzuo Lin
- David AlumbaughDADavid Alumbaugh
Preprint
Abstract
The carbon capture, utilization, and storage (CCUS) framework is an essential component in reducing greenhouse gas emissions, with its success hinging on the comprehensive knowledge of subsurface geology and geomechanics. Passive seismic event relocation and fault detection serve as indispensable tools, offering vital insights into subsurface structures and fluid migration pathways. Accurate identification and localization of seismic events, however, face significant challenges, including the necessity for high-quality seismic data and advanced computational methods. To address these challenges, we introduce a novel deep learning method, DeFault, specifically designed for passive seismic source relocation and fault delineating for passive seismic monitoring projects. By leveraging data domain-adaptation, DeFault allows us to train a neural network with labeled synthetic data and apply it directly to field data. Using DeFault, the passive seismic sources are automatically clustered based on their recording time and spatial locations, and subsequently, faults and fractures are delineated accordingly. We demonstrate the efficacy of DeFault on a field case study involving CO2 injection related microseismic data from the Decatur, Illinois area. Our approach accurately and efficiently relocated passive seismic events, identified faults and aided in the prevention of potential geological hazards. Our results highlight the potential of DeFault as a valuable tool for passive seismic monitoring, emphasizing its role in ensuring CCUS project safety. This research bolsters the understanding of subsurface characterization in CCUS, illustrating machine learning's capacity to refine these methods. Ultimately, our work bear significant implications for CCUS technology deployment, an essential strategy in combating climate change.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Machine learning in microseismic monitoringEarth-Science Reviews, 2023
- MLReal: Bridging the gap between training on synthetic data and real data applications in machine learningArtificial Intelligence in Geosciences, 2022
- Influence of Fault Architecture on Induced Earthquake Sequence Evolution Revealed by High‐Resolution Focal Mechanism SolutionsJournal of Geophysical Research: Solid Earth, 2022
- Iterative passive-source location estimation and velocity inversion using geometric-mean reverse-time migration and full-waveform inversionGeophysical Journal International, 2020
- Petrology, geochronology, and geophysical characterization of Mesoproterozoic rocks in central Illinois, USAGeoscience Frontiers, 2020
- Illinois Basin–Decatur Project2019
- Overview of microseismic response to CO2 injection into the Mt. Simon saline reservoir at the Illinois Basin-Decatur ProjectInternational Journal of Greenhouse Gas Control, 2016
- Assessing induced seismicity risk at CO2 storage projects: Recent progress and remaining challengesInternational Journal of Greenhouse Gas Control, 2016
- Directly imaging steeply-dipping fault zones in geothermal fields with multicomponent seismic dataGeothermics, 2015
- Monitoring of induced seismicity during the first geothermal reservoir stimulation at Paralana, AustraliaGeothermics, 2014