How better mineral exploration makes better batteries
Finding and extracting deposits of cobalt, lithium, nickel and other materials used in batteries is an expensive and environmentally fraught proposition. Geoscientists are now applying artificial intelligence to quickly identify new resources, get the most out of those we already know about and improve refining processes.
It has been said that batteries hold the key to a sustainable future.
But so-called “clean energy” does not come without environmental costs. For instance, says Stanford geoscientist Jef Caers, the batteries in a single Tesla contain some 4.5 kilograms — about 10 pounds — of cobalt, in addition to plenty of lithium and nickel, too.
With some 300 million cars in the U.S. right now, a full transition to electric vehicles would be impossible without new resources. But, finding new deposits and getting them safely out of the ground is an expensive and environmentally fraught proposition. Half of all cobalt reserves and most of current production come from just one unregulated country, Congo. To close the gap using environmentally and labor-regulated resources, Caers says we need AI to rapidly explore countries with stricter safeguards.
To help, geoscientists like Caers are turning to data science and artificial intelligence to quickly identify new resources, to get the most out of those we already know about and to improve refining processes to leave as small an environmental footprint as possible. Their success, he says, could be key to America’s environmental future and its long-term energy independence.
Learn more on this episode of Stanford Engineering’s The Future of Everything podcast, hosted by Stanford bioengineer Russ Altman. Listen and subscribe here.
Related research
Critical minerals scarcity could threaten renewable energy future
The supply chains for critical and rare minerals are vulnerable to political and economic disruptions that could hamper the global shift to a renewable energy future.
Training computer models to accurately simulate nature's variability
Borrowing insights from techniques used to image cancer, Stanford scientists have devised a new method for generating "training images" that can be used to fine-tune models of uncertainty about underground physical processes and structures.
Media Contacts
Josie Garthwaite
School of Earth, Energy & Environmental Sciences
(650)497-0947; josieg@stanford.edu
Jef Caers
School of Earth, Energy & Environmental Sciences
jcaers@stanford.edu
Explore More
-
Conventional sunscreen ingredients can damage coral reefs and human health. An immunologist and a marine ecologist teamed up to develop a better approach.
-
With support from a Stanford Doerr School of Sustainability Accelerator seed grant, an interdisciplinary team has developed a groundbreaking optical sensor that measures DNA and other key molecules in seawater using light, potentially revolutionizing the study of biodiversity in the enigmatic depths below the ocean’s surface.
