The Elements of Innovation Discovered
The Elements of Innovation Discovered
CriticalMAAS is processing data generated through USGS Earth MRI program, such as from the samples collected by geoscientist Jamey Jones from a mineralized outcrop in Alaska.
Critical mineral systems being explored by Earth MRI and to be assessed by CriticalMAAS.
A helicopter equipped to collect geophysical data for the USGS Earth MRI program from a critical mineral-enriched area spanning the Colorado-Wyoming border.
Amid the global race to secure minerals needed for clean energy technologies and national security, the U.S. Geological Survey (USGS) is leveraging the transformative abilities of artificial intelligence to analyze and assess the nation's critical mineral resources at a pace and scale never before possible.
"Typical mineral resource assessment will take us two years, start to finish, and that's just for one deposit type, which may contain one mineral commodity in one area of the country," said USGS Research Geologist Graham Lederer. "To assess 50 commodities across 100 deposit types throughout the entire United States would take many years to complete."
Lederer is leading a collaboration with the U.S. Defense Advanced Research Projects Agency (DARPA) and the Department of Energy's Advanced Research Projects Agency-Energy (ARPA-E) to utilize AI and machine learning tools to shorten the critical mineral assessment processes from years to days.
This collaborative project, known as the Critical Mineral Assessment with AI Support (CriticalMAAS), recently concluded a five-day "hackathon" workshop today that is serving as the launch pad for utilizing AI and machine learning to accelerate the critical mineral assessment process while also lightening the human workload.
This is not the first hackathon held by the CriticalMAAS collaborative.
Since February 2024, CriticalMAAS has completed a dozen pilot projects, demonstrating its ability to reduce assessment timelines from years to just 2.5 days. These include national-scale evaluations of zinc, copper, and nickel, as well as regional assessments of cobalt, lithium, tungsten, and rare earth elements.
Erica Briscoe, a program manager from DARPA's Information Innovation Office, says the results from these pilot-scale projects have been promising – condensing an entire critical minerals assessment into two days, from start to finish.
"So far, we've automated the process for pulling data from maps and documents and then compiling the data together and making it analysis-ready," she said. "The process is already moving much faster than expected."
The promising CriticalMAAS results are welcome news for USGS, which has been charged with assessing the domestic potential for 50 minerals deemed critical to the U.S. and has collected and compiled massive quantities of data for this task.
A helicopter equipped to collect geophysical data for the USGS Earth MRI program from a critical mineral-enriched area spanning the Colorado-Wyoming border.
Much of the new critical mineral data is being generated by the Earth Mapping Resources Initiative (Earth MRI), a nationwide program that USGS is carrying out in partnership with state geological surveys focused on gaining in-depth insights into the geology and critical minerals potential across the U.S.
Since the 2019 start of Earth MRI, roughly $200 million has been invested in or allotted to critical mineral assessments under this initiative.
While Earth MRI involves extensive mapping and sampling across the continental U.S. and Alaska, the largest investments have been made into the geophysical programs that provide geoscientists with 3D images of the subsurface and inspired the naming of the initiative.
Much like medical MRI machines provide detailed images inside the human body, the geophysical surveys carried out under Earth MRI utilize sensing equipment to provide images and information on buried rock formations that provide insights into the geology hidden below the Earth's surface.
Prior to the start of Earth MRI, only a small portion of the U.S. had been systematically scanned and mapped with modern technologies. Today, three times more of the nation is covered by high-quality surveys than when the initiative began in 2019.
This nationwide endeavor has generated a massive amount of data to process and understand. The use of AI under the CriticalMAAS collaborative is showing the capacity to transform this mountain of geophysical, geochemical, and mapping data into actionable insights that could speed the discovery and development of deposits enriched in the minerals critical to America's economy, security, and energy transition ambitions.
Critical mineral systems being explored by Earth MRI and to be assessed by CriticalMAAS.
The CriticalMAAS collaborative is using AI and machine learning to begin digesting and analyzing the wealth of critical minerals data generated by Earth MRI and gathered from other public and private sector mineral exploration endeavors.
While AI is doing the heavy lifting when it comes to data processing and analysis, the human element remains an essential part of the program.
Human-in-the-loop learning is being used for training and developing application-specific tools, and any critical minerals assessments generated by AI will need to be peer-reviewed to ensure the data and conclusions meet the USGS's strict scientific standards.
"Over time, we've built more precise and accurate extraction tools because of having human-in-the-loop," said Briscoe. "This human element also helps create better training data and customizable tools for further specific applications."
Once CriticalMAAS has been completed, the goal is for USGS scientists to be able to apply the AI model to the assessment of domestic minerals critical to America's economy, security, and clean energy ambitions.
The advancements made by CriticalMAAS and the geological data generated by Earth MRI are paving the way for quickly analyzing enormous loads of data to assess America's vast mineral potential.
"These investments, both to Earth MRI and to CriticalMAAS, are setting the groundwork for future generations of earth scientists," said Lederer.
With more than 16 years of covering mining, Shane is renowned for his insights and and in-depth analysis of mining, mineral exploration and technology metals.
Reader Comments(0)