On December 23, 2025, Tohoku University and Fujitsu Limited announced that they have successfully applied AI to derive new insights into the superconducting mechanism of a new superconducting material. Their findings demonstrate an important use of AI technology in new materials development and suggest that this technology has the potential to accelerate research and development. This has the potential to foster innovation in a variety of industries, including the environment and energy, drug discovery and healthcare, and electronics.
Utilizing AI technology, we automatically clarified causal relationships from measurement data obtained with the NanoTerrace synchrotron radiation source. This result was published in the Nature Portfolio scientific journal Scientific Reports on December 22, 2025.
The two companies leveraged Fujitsu's AI platform “Fujitsu Kozuchi” to develop a new discovery intelligence technology that accurately estimates causal relationships. Fujitsu will begin providing a trial environment for this technology from March 2026. Furthermore, in collaboration with Tohoku University Institute for Materials Research (WPI-AIMR), we applied this technology to measurement data from angle-resolved photoelectron spectroscopy (ARPES), an experimental method for materials research that observes the state of electrons in a specific superconducting material.
Tohoku University and Fujitsu established the “Fujitsu x Tohoku University Discovery Intelligence Laboratory'' in October 2022 as part of the “Fujitsu Small Research Institute'' initiative, which aims to have Fujitsu researchers stationed at the university to accelerate joint research, discover new themes, develop human resources, and build long-term relationships. The aim is to combine the technology, track record, and knowledge of Tohoku University and Fujitsu to contribute to solving social issues through the development of new technologies and human resource development. The two companies are conducting joint research aimed at the development and social implementation of discovery intelligence that utilizes AI to solve various problems, including materials science, from data.
The NanoTerrace synchrotron radiation source, which began operation in April 2024, is capable of measuring the states of molecules, atoms, and electrons with high spatial resolution at the nanometer level. The facility will work to develop new functional materials, promote innovation, and contribute to solving social issues such as environmental problems. However, as measurement performance increases, so does the amount of data created. Efficiently extracting only useful information without relying on human experience and intuition and automating scientific research processes will be key priorities for the future.
ARPES measurement data is extremely large. Data causality graphs have a huge number of nodes, making it difficult to find useful information. The technology developed in this joint research significantly reduces the scale of causal graphs by performing fitting on measured data based on model formulas and constructing causal graphs from only the extracted parameters. In addition, the parties have developed techniques to further simplify the graph and reduce the effects of noise. This technology reduces the size of causality graphs to less than 1/20 of conventional graphs, making it possible to efficiently discover new knowledge.
Tohoku University and Fujitsu applied this technology to ARPES measurement data of cesium vanadium antimonide (CsV3Sb5), a Kagome superconducting material. Cesium vanadium antimonide has potential applications as a high-temperature superconductor, but its superconducting mechanism is not yet fully understood. They discovered that the mechanism of superconductivity is due to the interaction of electrons in vanadium, antimony, and cesium.
Going forward, the two organizations will further leverage this technology and NanoTerasu's world-class spatial resolution capabilities to automatically uncover causal relationships between phenomena at the microscopic level. Through this, we will contribute to the development of new functional materials such as high-temperature superconductivity and next-generation low power consumption devices that solve global environmental problems, which is one of Fujitsu's material issues.
- Publication details:
title: Extracting causal relationships from spectroscopy
author: Kei Fujita, Kosuke Nakayama, Yuka Fujiki, Takemi Kato, Hiroshi Mizuto, Hiroyuki Higuchi, Takafumi Sato
journal: scientific report
Doi: 10.1038/s41598-025-29687-8
/Open to the public. This material from the original organization/author may be of a contemporary nature and has been edited for clarity, style, and length. Mirage.News does not take any institutional position or position, and all views, positions, and conclusions expressed herein are solely those of the authors. Read the full text here.
