NETL experts use advanced computing capabilities such as machine learning (ML) and artificial intelligence (AI) to analyze historical records, information reported by citizen scientists, field data collections, and other obscure We are developing a method to identify undocumented orphans by analyzing information from diverse data streams such as sources. Wells (UOW) lead to remediation efforts that can reduce greenhouse gas emissions.
The commonly accepted definition of UOW describes an idle well with an unknown or insolvent operator. Many of these wells leak greenhouse gases into the atmosphere and contribute to climate change.
It is estimated that there are as many as 800,000 UOWs scattered across the United States, and the locations and characteristics of these wells are not included in current digital records. Identifying these locations is critical so that wells can be plugged safely and effectively to reduce risks to the environment, climate, and human health and safety.
The Appalachian Basin has a long history of drilling, long before modern record-keeping techniques were established, and is expected to have a large number of UOWs. Further complicating the investigation is the fact that many properties have changed owners and operators multiple times, making it difficult to identify who is responsible for blockages and repair work.
Information about the location of many UOWs exists in the form of old land survey maps, drilling permits, historical images, production records, documented eyewitness accounts, and other items. Sophisticated computing techniques must be used to connect the pieces, locate them, and understand the properties of those wells. NETL experts build new features and adapt existing features to address problems.
Using AI A computer that performs functions that traditionally required human intelligence. AI can process large amounts of data in ways humans cannot. AI can recognize patterns, make decisions, and make judgments just like humans. ML is a branch of AI and computer science that focuses on using data and algorithms to mimic how humans learn, with incremental accuracy. Algorithms in ML are the steps performed on data to create ML models that perform pattern recognition functions. Basically, algorithms learn from data.
NETL’s Jennifer Bauer explains: Using supervised machine learning, the marks and symbols used to represent wells in these maps and images can be identified and processed to estimate potential well locations. The resurrected location can then be compared to modern records to determine if it is an undocumented well. ”
In parallel, NETL experts process well integrity test records to extract information about how wells were constructed, designed and executed. That information can be used to prioritize plug work so that targeted wells pose the greatest risk to the environment and human health and safety.
“A lot of this research is just beginning,” Bauer said. “However, unique capabilities and planned NETL facilities, such as the planned Joint Geosciences, Environmental and Materials (GEM) Computing Facility at NETL in Albany, Oregon, provide distributed computational analysis capabilities, Expand connectivity to additional data sources and collaborators to support development and use This includes applying multimodal machine learning to identify UOWs, which is common in ensemble learning It’s a similar approach that uses multiple data sources and models.”
She said multimodal machine learning models can be used to identify patterns and relationships that are not apparent to traditional methods or the human eye.
“By combining data from different sources within the model, we are able to obtain a more complete picture of patterns of well drilling trends across the country, and how these locations relate to changes in environment and population concentration over time. You can also show what you’re doing,” she said.
NETL’s expertise in high-performance computing is part of the Consortium Advancing Technology for Assessment of Lost, which comprises the Department of Energy’s national laboratories, including Berkeley Lab, Lawrence Livermore National Laboratory, Los Alamos National Laboratory, and Sandia National Laboratories. An integral part of Oil and Gas Wells (CATALOG). Institute. The creation of the CATALOG was required by the Bipartisan Infrastructure Act (BIL) and funding was provided to plug in the UOW. BIL noted that addressing UOW will help communities reduce methane emissions and eliminate other environmental impacts, while creating jobs and promoting environmental justice.
NETL is a national laboratory of the U.S. Department of Energy that drives innovation and provides technological solutions for an environmentally sustainable and prosperous energy future. Leveraging world-class talent and research facilities, NETL secures affordable, abundant and reliable energy that drives a robust economy and national security, while managing carbon throughout its lifecycle Developing technology to enable environmental sustainability for all Americans.
