started · updated
AI research focuses on magnetic efficiency and solar power integration
Researchers at the Tokyo University of Science have developed a physics-interpretable artificial intelligence approach to investigate the microscopic origins of high-frequency magnetic loss. Led by Professor Masato Kotsugi, the team used the Fugaku supercomputer to perform large-scale micromagnetic simulations. This method aims to identify specific microscopic structures that contribute to energy resistance during magnetization reversal, potentially leading to the design of more efficient magnetic materials for electric vehicles, renewable energy systems, and data centers.
Separately, the growing electricity demand for AI data centers is driving increased interest in solar energy. While AI systems require continuous power and solar generation is intermittent, companies like Google and Microsoft are increasingly utilizing solar power and battery storage to meet their energy needs. The International Energy Agency projects that global data center electricity consumption, which reached approximately 485 terawatt-hours in 2025, could rise to around 950 terawatt-hours by 2030.
Entities
Google · International Energy Agency · Masato Kotsugi · Microsoft · Tokyo University of Science