Machine learning approaches to identify lithium concentration in petroleum produced waters

• Published in: Mineral economics : raw materials report 2024-09, Vol.37 (3), p.477-497
• Main Authors: Attanasi, E. D., Coburn, T. C., Freeman, P. A.
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Brines; Chemical analysis; Concentration gradient; Crude oil; Data analysis; Economics; Economics and Finance; Engineering Economics; Environmental Economics; Gas wells; Geologic formations; Geological surveys; Industrial Organization; Innovation/Technology Management; Lithium; Logistics; Machine learning; Marketing; Mineral Resources; Natural gas; Oil and gas fields; Oil fields; Organization; Original Paper; Performance prediction; Petroleum; Water wells
• ISSN: 2191-2203; 2191-2211
• DOI: 10.1007/s13563-023-00409-8

Prices for battery-grade lithium have increased substantially since 2020, which is propelling the search for additional sources of this important element. Battery-grade lithium is predominately recovered from continental brines. Most crude oil and natural gas wells recover briny formation water, which may represent an additional source. Chemical analysis of these waters has been shown to indicate the presence of varying concentrations of lithium and related elements. This paper briefly reviews developments and literature supporting the presence of lithium in petroleum reservoir brines. It also describes the coverage and distribution of lithium data analyses in the United States Geological Survey National Produced Waters Geochemical Database (PWGD). It then addresses the question as to whether a lithium concentration can be accurately predicted using constituents of ion chemistry in produced brines from specific geologic formations. Four machine learning algorithms are employed to classify the commercial potential of lithium in oil field brines using data from oil wells recovering formation water from the Smackover Formation. The calibrated classification models are further applied to new (out-of-sample) data from the Marcellus Formation in the Appalachian Basin. Among the approaches considered, the predictive performance and wider applicability of the gradient boosted tree and the deep neural network models are determined to be the most promising. Finally, we discuss how the calibrated models could be applied to assure the quality of the data reported from chemical laboratory analysis and for imputation when lithium values are missing.