Researchers at the University of Liverpool say they have created a collaborative artificial intelligence tool that reduces the time and effort required to discover new materials. The innovation is part of the growing use of AI to help develop everything from new drugs to new batteries. “Thanks to high-performance software tools, processing power, and cheap memory, AI can fully automate complex tasks and provide consistent and precise discoveries,” Matthew Putman, the CEO of Nanotronics, a company that uses AI, told Lifewire in an email interview. “It requires less manpower to maintain and can be adjusted quickly when manufacturing strategies and production plans are altered.”
Material World
According to a recent paper in Nature Communications, the researchers at the University of Liverpool have already used their new AI tool. The team discovered four new materials, including a new family of solid-state materials that conduct lithium. The materials could be critical to developing batteries that offer a longer range and increased safety for electric vehicles. The AI tool examines the relationships between known materials faster than humans. These relationships are used to find and rank combinations of elements that are likely to form new materials. Scientists use the rankings to guide the exploration of the unknown chemical space in a targeted way, making experimental investigation far more efficient. Those scientists make the final decisions, informed by the information offered by AI. “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,” Matt Rosseinsky, the lead author of the paper, said in a news release. “We, therefore, need new tools that reduce the time and effort required to discover truly new materials, such as the one developed here that combines artificial intelligence and human intelligence to get the best of both.” AI-identified materials have been fabricated for new Li-ion electrodes of the kind that are sometimes used in consumer electronics, Emily Ryan, an engineering professor at Boston University who works on AI-assisted discovery of new technologies, told Lifewire in an email interview. She was not involved in the Liverpool research. “Although still in the research and development stages, they show promise,” she said. “I am not sure about the timeline to commercialization, but materials development is usually a 10-year plus process.”
AI Accelerators
Companies across the globe have doubled down on AI-driven strategies in the production of materials, and consumers already see the benefits, Putman said. “Scientists are using databases to predict which compounds might create new and exciting materials,” he added. “They can create a shortcut with AI to create super-strong materials—and the AI will tell the scientists the best experiment to run to make the new material.” Machine learning and AI are being applied across many fields, including health applications and energy. “In the search for better energy storage, AI methods are being applied to explore new electrolyte and electrode materials to improve the performance and extend the life of next-generation batteries,” Ryan said. “AI and ML are being applied to high throughput computing to identify novel materials that could possibly replace current electrolyte and electrode materials.” But there is a dark side to the use of AI for discovery, Joshua M. Pearce, an engineering professor at Western University, told Lifewire in an email interview. Some researchers are trying to use AI as patent robots to monopolize advanced materials. Pearce recently wrote a paper describing how early patenting of basic building blocks fouled up nanotechnology and slowed its progress. “This is a real risk in material science,” he added. “In 3D printing, someone in Europe tried to patent the use of all thermoplastics for additive manufacturing, which is the basic process we all use.”
