Enhancing knowledge discovery from unstructured data using a deep learning approach to support subsurface modeling predictions

Brendan Hoover; Dakota Zaengle; MacKenzie Mark-Moser; Patrick Wingo; Anuj Suhag; Kelly Rose

doi:10.3389/fdata.2023.1227189

Enhancing knowledge discovery from unstructured data using a deep learning approach to support subsurface modeling predictions

Front Big Data. 2023 Dec 19:6:1227189. doi: 10.3389/fdata.2023.1227189. eCollection 2023.

Authors

Brendan Hoover^{1

2

3}, Dakota Zaengle^{1

2}, MacKenzie Mark-Moser^{1

2}, Patrick Wingo^{1

2}, Anuj Suhag¹, Kelly Rose¹

Affiliations

¹ National Energy Technology Laboratory, Albany, OR, United States.
² NETL Support Contractor, Albany, OR, United States.
³ US Army Corps of Engineers, Geospatial Research Laboratory, Alexandria, VA, United States.

Abstract

Subsurface interpretations and models rely on knowledge from subject matter experts who utilize unstructured information from images, maps, cross sections, and other products to provide context to measured data (e. g., cores, well logs, seismic surveys). To enhance such knowledge discovery, we advanced the National Energy Technology Laboratory's (NETL) Subsurface Trend Analysis (STA) workflow with an artificial intelligence (AI) deep learning approach for image embedding. NETL's STA method offers a validated science-based approach of combining geologic systems knowledge, statistical modeling, and datasets to improve predictions of subsurface properties. The STA image embedding tool quickly extracts images from unstructured knowledge products like publications, maps, websites, and presentations; categorically labels the images; and creates a repository for geologic domain postulation. Via a case study on geographic and subsurface literature of the Gulf of Mexico (GOM), results show the STA image embedding tool extracts images and correctly labels them with ~90 to ~95% accuracy.

Keywords: artificial intelligence; deep learning; knowledge discovery (data mining); modeling; subsurface; unstructured data.

Grants and funding

This project was funded by the U.S. Department of Energy, National Energy Technology Laboratory, in part, through a site support contract. Neither the United States Government nor any agency thereof, nor any of their employees, nor the support contractor, nor any of their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.