Agentic AI accelerates search for crops that can harvest critical minerals
For too long, the United States has relied on foreign sources for most of the raw materials powering its technological future: the essential minerals in every smartphone, battery pack and semiconductor. What if one answer to the supply crisis isn't buried in a mine shaft but growing quietly in a field? Scientists are betting on a resource-efficient, highly effective strategy: using engineered…
The United States has long depended on foreign sources for minerals used in technology, like those in smartphones and batteries. A promising solution may come from plants that absorb critical minerals from the soil in a process called phytomining. At Oak Ridge National Laboratory (ORNL), researchers are using artificial intelligence to accelerate the search for crops that can selectively absorb these minerals.
This AI-powered system, called the Orchestrated Platform for Autonomous Laboratories (OPAL), utilizes the Frontier supercomputer to train and generate insights for biologists and computational scientists at ORNL and partner labs. The goal is to develop plants that act as "living sponges," hyperaccumulating critical minerals like nickel, cobalt, selenium, and rare earth elements.
In an experiment on pennycress plants, OPAL's agentic AI co-scientist reduced the time to analyze over 1,000 plant traits from hundreds of manual labor hours to just a few minutes. The AI system identified plant traits, anomalies, and suggested follow-up experiments to improve nickel phytomining strategies. The data collected from the experiment was used to create an AI-ready data set shared across multiple laboratories.
Phytomining is not new, but combining it with AI and robotics could make it more efficient and economical. The technology could benefit rural economies, strengthen domestic supply chains, and help with energy and national security needs by utilizing low-grade mineral deposits in marginal lands or rehabilitation zones for existing mining operations.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
