Two newly discovered superconductors highlight the potential of machine learning to accelerate materials discovery.
Scientists at Aalto University have discovered two new superconductors, YRu3B2 and LuRu3B2. In this process, machine learning methods and quantum physics calculations were applied, which helped to speed up research significantly.
As for the new superconductors, they possess their superconducting qualities due to the specific configuration of electrons forming a so-called kagome lattice. A Kagome lattice is a structure named after a traditional Japanese basket-weaving pattern. In order to confirm the most promising materials, after being identified using machine learning, scientists used theoretical calculations, and then created the materials and verified them with experiments. This discovery became possible within the framework of the SuperC consortium project, which was launched in 2023 with the goal of discovering a room-temperature superconductor by 2033.
“Superconductive materials that can operate at room temperature would forever change the way we consume energy,” explained Aalto University Professor Päivi Törmä. “If such a material could replace regular conductors in applications like computers and data centres, global energy consumption could be slashed and the heat footprint from the ICT sector vastly reduced.”
Superconducting materials can conduct electricity without any resistance at very low temperatures. Such materials are currently being used in advanced technologies including quantum computing, MRI scanners, fusion reactors, and magnetic levitation trains. It has always been a quest for scientists to find superconducting materials which remain superconductive at room temperatures because their applications can revolutionize the world.
“Over the decades, researchers have recognised over 7,000 superconductors, but mostly serendipitously,” explained Törmä. “The process of identifying possible materials is so computationally heavy that, in fact, researchers have only been able to theoretically predict the viability of about 20 of these.”
“Our method uses machine-learning-based pre-screening followed by targeted calculations on the promising candidates. This approach will greatly speed up superconductor discovery in the future. With machine learning, we may be able to push the number of materials we can process into the billions,” said Törmä. “This will take us a critical step closer to finding a room-temperature superconductor.”
