Researchers reveal an atomic manufacturing technology based on artificial intelligence

Researchers from the National University of Singapore (NUS) have developed an innovative method to create carbon-based quantum materials corn For every atom. This method combines the use of scanning microscopy with advanced deep neural networks. This achievement highlights the capabilities of artificial intelligence (AI) to manipulate materials on a sub-angstrom scale, providing significant benefits for basic science and potential future uses.

Open-shell magnetic nanographs represent a technically attractive class of new carbon-based quantum materials, which host strong spin centers and non-trivial collective quantum magnetism. These properties are crucial for the development of high-speed electronic devices at the molecular level and the creation of quantum bits, the building blocks of quantum computers.

Although there has been significant progress in fabricating these materials through facile synthesis, a type of chemical reaction in the solid phase, fabrication and tailoring of the properties of these quantum materials precisely at the atomic level remains a challenge.

The figure shows an intuitive atomic robotic probe that will allow chemists to manufacture organic quantum materials with precision at the single-molecule level. The robotic probe can perform independent, real-time reactions on a single molecule with selectivity for chemical bonds, demonstrating the fabrication of quantum materials with a high level of control. Credit: Nature Synthesis

Carp concept

The research team, led by Associate Professor Lu Jeong from the Department of Chemistry at the National University of Singapore and the Institute for Functional Smart Materials, together with Associate Professor Chang Chun from the Department of Physics at the National University of Singapore, presented the probe concept for Intuitive Atomic Robotics by Chemists (CARP). ) by integrating the probe's chemical knowledge and artificial intelligence to fabricate and characterize open-shell magnetic nanographene at the single molecule level. This allows precise engineering of electron topologies and spin configurations in an automated manner, mirroring the capabilities of human chemists.

Demonstration of automated atomic probes driven by artificial intelligence and intuitive by chemists. Credit: Nature Synthesis

The CARP concept uses deep neural networks trained using the experience and knowledge of surface science chemists, to autonomously fabricate open-shell magnetic nanographenes. It can also extract chemical information from an experimental training database, providing insight into unknown mechanisms. This constitutes an essential complement to theoretical simulations, contributing to a more complete understanding of the chemical reaction mechanisms of the probes. The research work is a collaboration involving Associate Professor Wang Xiaonan from Tsinghua University in China.

Publishing and capabilities

The research results were recently published in the journal Natural synthesis.

The researchers tested the CARP concept on a complex in situ selective hydrocyclohydrogen reaction used to produce chemical compounds with specific structural and electronic properties. The results show that the CARP framework can effectively take a scientist's expert knowledge and transform it into machine-understandable tasks, simulating workflows for performing single-molecule reactions capable of manipulating the geometry and rotational properties of the final chemical compound.

Furthermore, the research team aims to harness the full potential of AI capabilities by extracting hidden information from the database. They created an intelligent learning model using a game theory-based approach to examine the learning outcomes of the framework. The analysis shows that CARP has effectively captured important details that humans might miss, especially when it comes to successfully completing the cyclohydrogenation reaction. This suggests that the CARP framework can be a valuable tool to gain additional insights into the mechanisms of unexplored single-molecule interactions.

Associate Professor Lu said: “Our main goal is to work at the atomic level to create, study and control these quantum materials. We are working to revolutionize the production of these materials on surfaces to enable greater control of their results, down to the level of individual atoms and bonds.

“Our goal in the near future is to expand the CARP framework to include versatile chemical reactions using surface sensors with scale and efficiency. This has the potential to shift the traditional in vitro surface synthesis process towards on-chip fabrication for practical applications. Such a transformation could “To play a pivotal role in accelerating fundamental research in quantum materials and ushering in a new era of intelligent atomic manufacturing.”