An AI Dreamed Up 380,000 New Materials. The Next Challenge Is Making Them

The robotic line cooks were hard at work in a room packed with equipment. An articulated arm selected and mixed ingredients, while another worked the ovens back and forth on a fixed track. A third arm was on plating duty. Gerbrand Ceder, a materials scientist at Lawrence Berkeley Lab and UC Berkeley, watched as a robotic arm delicately pinched and capped an empty plastic vial. “These guys can work all night,” Ceder said, giving two of his grad students a wry look.

The facility, called the A-Lab, is designed to create new and interesting materials, particularly those that might be useful for future battery designs. The results are unpredictable, much like a new recipe made by a human. Sometimes the robots produce a beautiful powder, while other times it’s a melted mess, or it all evaporates and there’s nothing left. “At that point, the humans would have to make a decision: What do I do now?” Ceder says.

The robots analyze what they’ve made, adjust the recipe, and try again and again. “You give them some recipes in the morning and when you come back home you might have a nice new soufflé,” says materials scientist Kristin Persson, Ceder’s close collaborator at LBL. Or you might just return to a burned-up mess. “But at least tomorrow they’ll make a much better soufflé.”

Video: Marilyn Sargent/Berkeley Lab

Recently, the range of dishes available to Ceder’s robots has grown exponentially, thanks to an AI program developed by Google DeepMind. Called GNoME, the software was trained using data from the Materials Project, a free-to-use database of 150,000 known materials overseen by Persson. Using that information, the AI system came up with designs for 2.2 million new crystals, of which 380,000 were predicted to be stable—expanding the range of known stable materials nearly 10-fold. In a paper published today in Nature, the authors write that the next solid-state electrolyte, solar cell materials, or high-temperature superconductor could hide within this expanded database.

Finding those needles in the haystack starts with actually making them, which is all the more reason to work quickly and through the night. In a recent set of experiments at LBL, also published today in Nature, Ceder’s autonomous lab was able to create 41 of GNoME’s theorized materials over 17 days, helping to validate both the AI model and the lab’s robotic techniques.

When deciding if a material can actually be made, among the first questions to ask is whether it is stable. Generally, that means its atoms are arranged into the lowest possible energy state. Otherwise, the crystal will want to become something else. For thousands of years, people have steadily added to the roster of stable materials, initially by observing those found in nature or discovering them through basic chemical intuition or accidents. More recently, candidates have been designed with computers.

The problem, according to Persson, is bias: Over time, collective knowledge has come to favor certain familiar structures and elements. Materials scientists call this the “Edison effect,” referring to his rapid trial-and-error quest to deliver a lightbulb filament. It took another decade for a Hungarian group to come up with tungsten. “He was limited by his knowledge,” Persson says. “He was biased, he was convinced.”

Source link

Leave a Comment