Geology ReportsSearch

EXPLORE THE ARCHIVE

Garth E. Graham

Publications and source records attributed to Garth E. Graham.

2 recordsLinked to original sources

Critical Minerals in Ores (CMiO) database

Critical minerals are commodities essential to modern industrial and strategic technologies and are highly vulnerable to supply chain disruption. The Critical Minerals Mapping Initiative (CMMI) is a collaboration among the U.S. Geological Survey (USGS), the Geological Survey of Canada, and Geoscience Australia that aims to deepen global understanding of where critical minerals are located. A key output of this initiative is the Critical Minerals in Ores (CMiO) database that is advancing our collective understanding of critical minerals distributions. For instance, publicly available data on the concentrations of many critical minerals are sparse because these commodities can only be produced in small, yet essential, quantities compared to the primary commodities like copper and zinc. The CMiO database helps bridge this gap by offering high-quality, multielement geochemical data from a wide variety of critical mineral-bearing deposits around the world. Importantly, it uses a novel consensus deposit environment, group, and type classification scheme developed by the agencies that allows comparisons among ore deposits from different regions. The CMiO database contains geochemical data for more than 20,000 samples from more than 100 deposit types comprising 10 deposit environments.

Fact Sheet

Extracting data from maps: Lessons learned from the artificial intelligence for critical mineral assessment competition

The U.S. Geological Survey (USGS), Defense Advanced Projects Research Agency (DARPA), NASA Jet Propulsion Laboratory (JPL), and MITRE ran a 12-week machine learning competition aimed at accelerating development of AI tools for critical mineral assessments. The Artificial Intelligence for Critical Mineral Assessment Competition solicited innovative solutions for two challenges: 1) automated georeferencing of historical maps, and 2) automated feature extraction from historical maps. Competitors used a new dataset of historical map images to train, validate, and evaluate their models. Automated georeferencing pipelines attained a median root-mean square error of 1.1 km. Prompt-based extraction (i.e., with user input) of polygons, polylines, and points from geologic maps yielded median F1-scores of 0.77, 0.56, 0.35, respectively. Geologic maps pose numerous challenges for AI workflows because they vary significantly. However, despite its short duration, the competition yielded promising results that have since spurred further innovation in this area and led to the development of new AI tools to semi-automate key, time-consuming parts of the assessment workflow.

Applied Computing and Geosciences