AI automates the creation of custom functional materials atom by atom
Imagine a construction site where the bricks are individual molecules and the "cranes" are microscopic needles so sharp they can feel a single atom. For decades, building at this scale was a laborious, time-consuming task where a single human error could damage the delicate tools.
Researchers at Oak Ridge National Laboratory have developed an AI system capable of autonomously constructing functional materials atom by atom. This breakthrough, published in ACS Nano, marks a significant shift from discovering materials in nature to engineering artificial lattices with tailored electronic properties. Utilizing a combination of computer vision and reinforcement learning, the AI models act as microscopic "eyes" and brain, detecting molecules on a copper surface and learning the optimal strategies for positioning them.
The system successfully created a precise honeycomb pattern of 37 molecules, forming an artificial graphene lattice that exhibited the same electronic behavior as real graphene. While the process currently requires occasional human intervention to maintain the microscope tip, it promises to accelerate the development of advanced materials for high-speed electronics and quantum computing.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
