GSA Annual Meeting in Indianapolis, Indiana, USA - 2018

Paper No. 3-9
Presentation Time: 10:35 AM

UNEARTHING SUBSURFACE DATA USING INTELLIGENT GEOINFORMATICS (Invited Presentation)


ROSE, Kelly1, BAUER, Jennifer1, BAKER, D.V.2, ROWAN, Chad3 and JONES, Timothy2, (1)Department of Energy, National Energy Technology Laboratory, 1450 SW Queen Avenue, Albany, OR 97321, (2)MATRIC, Morgantown, WV 26505, (3)Attain, Contractor to, National Energy Technology Laboratory, 1450 SW Queen Avenue, Albany, OR 97321

The data revolution has resulted in a proliferation of resources that spans beyond commercial and social networking domains. Research, scientific, and engineering data resources, including subsurface characterization, modeling, and analytical datasets, are increasingly available through online portals, warehouses, and systems. Data for subsurface systems is still challenging to access, discontinuous, and varies in resolution. However, with the proliferation of online data there are significant opportunities to advance access and knowledge of subsurface systems. DOE’s Energy Data eXchange (EDX) is an online data computing platform designed to improve access to energy R&D products, support multi-organizational R&D through virtual sharing and analytical capabilities.

Since 2011, the EDX team has been developing a virtual subsurface digital library and laboratory to support subsurface energy research. The system serves both structured and unstructured data about subsurface systems. These resources span petrophysical, geologic, engineering, geophysical, interpretations, models, and analyses associated with carbon storage, water, oil, gas, geothermal, induced seismicity and other subsurface systems to support the development of a virtual subsurface data framework.

There are numerous challenges associated with finding and serving these data for our research community. However, the team has initiated development of custom machine learning algorithms to enhance user experience, make access to relevant, open-source, subsurface data resources more efficient. One of these tools, SmartSearch, is a machine learning, online, search tool designed to parse worldwide web to find online, .Zip, and FTP spatial and nonspatial data. SmartSearch was recently employed and tested by NETL researchers in the rapid effort that resulted in the development of a global oil and gas infrastructure, open-source database containing more than 2 million attributes in less than four months. EDX content and capabilities, such as SmartSearch, are continuously evolving. However, development of these types of advanced custom data computing tools will improve access and knowledge of data pertinent to subsurface research.