acm-header
Sign In

Communications of the ACM

ACM TechNews

Researchers Monitor Subsurface CO2 Storage


Unsupervised machine learning methods led to rapid and accurate monitoring and modeling of carbon dioxide movements in a subsurface geological sequestration site.

Credit: Getty Images

Texas A&M University researchers demonstrated that unsupervised machine learning algorithms could analyze data from a geological carbon sequestration site to determine and model underground carbon dioxide (CO2) plume locations and movements.

The algorithms evaluate CO2 presence in the data using five broad or qualitative ranges, identified by color for a two-dimensional visual representation; their results accelerated the pinpointing of plume location, coverage area, and its approximate size, shape, and density.

Texas A&M's Siddarth Misra said, "We are letting the data tell us where the CO2 actually is. We are also providing rapid visualization because if you cannot see the CO2, you cannot control it deep underground."

From Texas A&M Today
View Full Article

 

Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account