Input Files and Code for: Machine learning can accurately assign geologic basin to produced water samples using major geochemical parameters

As more hydrocarbon production from hydraulic fracturing and other methods produce large volumes of water, innovative methods must be explored for treatment and reuse of these waters. However, understanding the general water chemistry of these fluids is essential to providing the best treatment options optimized for each producing area. Machine learning algorithms can often be applied to datasets to solve complex problems. In this study, we used the U.S. Geological Survey’s National Produced Waters Geochemical Database (USGS PWGD) in an exploratory exercise to determine if systematic variations exist between produced waters and geologic environment that could be used to accurately classify a water sample to a given...

Categories: Data; Tags: Alabama, Alaska, Alaska Region, Arizona, Arkansas, All tags... California, Colorado, Colorado Plateau and Basin and Range Region, Eastern Region, Energy Resources, Florida, Geochemical analysis, Geochemistry, Georgia, Gulf Coast Region, Idaho, Illinois, Indiana, Iowa, Kansas, Kentucky, Louisiana, Lousiana, Machine learning, Maryland, Michigan, Mid Continent Region, Mississippi, Missouri, Montana, Naïve Bayes, Nebraska, Nevada, New Mexico, New York, North Dakota, Ohio, Oklahoma, Ontario, Oregon, Pacific Coast Region, Pennsylvania, Produced waters, Random Forest, Rocky Mountains and Northern Great Plains Region, Saskatchewan, South Dakota, Tennessee, Texas, USGS Science Data Catalog (SDC), Utah, Virginia, Washington, West Texas and Eastern New Mexico Region, West Virginia, Wyoming, geochemistry, k-Nearest Neighbors, Fewer tags