TLDR: Researchers at the University of Liverpool have developed a collaborative artificial intelligence tool that significantly reduces the time and effort required to discover novel materials. This innovative tool combines AI capabilities with human expertise to prioritize unexplored regions of chemical space, leading to the identification of new functional materials. Among its initial successes is the discovery of a new family of solid-state materials that conduct lithium, which are vital for the advancement of longer-range and safer electric vehicle batteries.
A groundbreaking collaborative artificial intelligence (AI) tool, developed by researchers at the University of Liverpool, is set to revolutionize the discovery of new materials. The tool, which integrates AI with human knowledge, aims to drastically cut down the time and effort traditionally associated with finding truly novel materials. This development was reported in the journal Nature Communications on September 21, 2021.
The new AI tool has already demonstrated significant success, leading to the discovery of four new materials. Notably, it has identified a new family of solid-state materials capable of conducting lithium. These solid electrolytes are considered crucial for the next generation of solid-state batteries, promising enhanced range and increased safety for electric vehicles. Further promising materials are currently under development.
Professor Matt Rosseinsky, lead author of the paper and head of the research team from the University of Liverpool’s Department of Chemistry and Materials Innovation Factory, highlighted the limitations of traditional material design. “To date, a common and powerful approach has been to design new materials by close analogy with existing ones, but this often leads to materials that are similar to ones we already have,” Professor Rosseinsky stated. He emphasized the necessity for new tools that can accelerate the discovery of genuinely new materials, such as the one developed by his team, which synergizes artificial and human intelligence.
Discovering new functional materials is inherently a high-risk, complex, and often protracted process due to the vast, almost infinite, chemical space available by combining elements from the periodic table. The location of new materials within this space is largely unknown. The Liverpool AI tool addresses this challenge by examining the intricate relationships between hundreds of thousands of known materials—a scale unachievable by human analysis alone. It then uses these relationships to identify and numerically rank combinations of elements most likely to form new materials.
This ranking system guides scientists in their exploration of the vast unknown chemical space, making experimental investigations significantly more efficient. The ultimate decisions, however, remain with human scientists, who leverage the unique perspective offered by the AI. Professor Rosseinsky described this as a collaborative approach that harnesses the computational power to analyze massive datasets and the critical thinking and expert knowledge of human researchers to drive creative advances.
He further noted, “This tool is an example of one of many collaborative artificial intelligence approaches likely to benefit scientists in the future.” The societal impact of such discoveries is profound, as the ability to design and create materials with targeted functions—such as improved solar absorbers for better solar panels or superior battery materials for longer-range electric cars—is critical for addressing global challenges like energy and sustainability. The development of lithium-ion batteries in the 1980s, which enabled modern portable electronics, underscores how a single material class can transform daily life, suggesting that accelerated routes to new materials will unlock unimaginable technological possibilities.
Also Read:
- MIT Researchers Unveil SCIGEN: A Generative AI Tool for Accelerating Breakthrough Quantum Material Discovery
- Unlocking Material Design: A New AI Model Explains How Nanoporous Structures Work
The research paper, titled ‘Element selection for crystalline inorganic solid discovery guided by unsupervised machine learning of experimentally explored chemistry,’ was published with the DOI: 10.1038/s41467-021-25343-7. Support for this research was provided by the Engineering and Physical Sciences Research Council, the Leverhulme Trust, and the Faraday Institution. The Materials Innovation Factory, a collaboration between the University of Liverpool and Unilever, combines materials chemistry expertise with advanced computational and robotic methodologies to accelerate research and product development.
