29 FEBRUARY 2025 WorldWide Drilling Resource® Using Modern Tools to Locate Undocumented Wells ~ Part 1 Adapted from Information by Berkeley Lab Remnants from almost 170 years of commercial drilling are scattered across the United States, with hundreds of thousands of abandoned gas and oil wells posing environmental and climate hazards. To identify undocumented orphaned wells (UOWs) and measure methane emissions in the field, researchers are using modern technologies, including drones, laser imaging, and sensors, along with artificial intelligence (AI) and historical topographic maps to predict their locations. Fabio Ciulla, a postdoctoral fellow at the Department of Energy’s Lawrence Berkeley National Laboratory (Berkeley Lab) pulled together rectangular maps covering a set latitude and longitude and mapped it at a scale where one inch represents 2000 feet. Between 1947 and 1992, these maps also used a hollow black circle for gas and oil wells. “For a human being, looking at this circle and recognizing it, is extremely easy,” Ciulla said. “Until recently, this was the only available method to extract information from these maps, but that strategy does not scale well if we want to apply it to thousands of maps. This is where artificial intelligence comes into play.” Researchers created a training set for AI by manually marking oil wells on nearly 100 California maps using a digital tool, enhancing the AI to identify hollow circles while ignoring false positives, such as cul-de-sacs or symbols with circular patterns, like the number 9 or letter “o”, and the algorithm could be applied to any of the United States Geological Survey (USGS) maps with the same symbols. Because the maps were georeferenced, the algorithm could take the coordinates for the oil wells marked on the map and compare them with coordinates for documented wells. To make this approach work, the Berkeley Lab research team had to train the AI to recognize the correct symbols, adjust other visual information, and work with maps featuring diverse terrain, colors, and conditions, including old, new, stained, and pristine maps. The team chose well symbols located more than 328 feet from known wells to identify potential undocumented orphan wells, considering possible errors in well coordinates. Furthermore, they developed a novel tool that enables humans to quickly verify the algorithm’s findings, ensuring accurate interpretation of map symbols. The researchers utilized an AI algorithm to search four counties with notable early oil production, finding 1301 potential UOWs in Los Angeles and Kern counties, in California, as well as Osage and Oklahoma counties, in Oklahoma. “With our method, we were conservative about what would be considered as a potential undocumented orphaned well,” said Charuleka Varadharajan, a scientist at Berkeley Lab and senior author of the study. “We intentionally chose to have more false negatives than false positives, since we wanted to be careful about the individual well locations identified through our approach. We think that the number of potential wells we’ve found is an underestimate, and we might find more wells with more refinement of our methods.” So far, researchers have verified 29 of the UOWs using satellite images and another 15 from surveys in the field; additional investigation on the ground will be needed to confirm other potential wells. Next month, we’ll discuss how researchers use their findings from the maps and apply the information in the field. Photo courtesy of Jeremy Snyder with Berkeley Lab. ENV USGS quadrangle maps from 1947-1992. Photo courtesy of the Historical Topographic Map Collection/USGS. j Sand j Manholes j Bentonite j Filter Sock j Sampling Bailers j Clear PVC Pipe j Locking Caps Atlantic Screen & Mfg., Inc. Manufacturers of Slotted & Perforated Pipe Ranging from 1/2” to 24” in Diameter 302-684-3197 FAX 302-684-0643 142 Broadkill Rd j Milton, DE 19968 www.atlantic-screen.com e-mail:atlantic@ce.net
RkJQdWJsaXNoZXIy NDk4Mzk=