Abstract
Eighty percent of current world energy consumption is satisfied by subsurface resources. In future, billions of watts of electrical power will be generated from geothermal energy sources. Subsurface earth can store the energy produced from renewable sources, such as wind and solar, and could provide safe storage of contaminants and hazardous nuclear waste. Engineering of subsurface earth is critical for fossil energy production, geothermal energy production, and carbon geo-sequestration. However, the subsurface is opaque, inaccessible, and heterogenous with nano-scale to kilo-scale processes that limits our understanding (characterization) and constrains the efficient engineering of the complex subsurface earth resources. There has been rapid increase in sensor deployment, data acquisition, data storage, and data processing for purposes of better engineering and characterizing the subsurface earth. This has promoted large-scale deployment of data-driven methods, machine learning, and data analytics workflows. Subsurface data ranges from nano-scale to kilometer-scale passive as well as active measurements. Subsurface data is acquired in the form of physical fluid/solid samples, images, 3D scans, time-series data, waveforms, and depth-based multi-modal signals, to name a few. Subsurface data sense various physical phenomena, e.g., transport, chemical, mechanical, electrical, and thermal properties. Integration of such varied data sources being acquired at varying scales, rates, resolutions, and volumes mandates robust machine learning methods to better characterize and engineer the subsurface earth. Machine learning has shown to improve the efficiency, efficacy, and productivity of subsurface engineering and characterization efforts required to produce fossil/geothermal energy and to sequester carbon dioxide.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
