ADVANCED MATERIALS & PROCESSES | SEPTEMBER 2026 10 MACHINE LEARNING | AI/FEEDBACK MACHINE LEARNING SPEEDS QUANTUM MATERIALS RESEARCH Scientists at The University of Manchester developed a computational approach to help identify 2D materials that may host unusual quantum behavior. The research focuses on materials with “flat bands,” electronic states where electrons have very little kinetic energy. In these materials, interactions between electrons can become much more important, creating conditions linked to properties like magnetism and unconventional superconductivity. Finding materials with flat bands from a large dataset is difficult. Traditional searches often rely on density functional theory calculations, which can reveal a material’s electronic structure but are time-consuming. Instead, the team developed a physics-informed scoring system that captures two signatures of flat-band behavior, low band dispersion, and a strong peak in the density of states, then trained a model to estimate that score directly from atomic structure. The framework was trained using known 2D materials and then applied to more than 10,000 unlabeled ones. Among high-scoring candidates, calculations confirmed flatband behavior with 98.2% accuracy. www.manchester.ac.uk. AI TOOL SUPPORTS PERMANENT MAGNET DESIGN Researchers at Ames National Laboratory are advancing the discovery of materials for rare-earth-free permanent magnets by combining fundamental physics with artificial intelligence (AI). Scientists are combining physics-based modeling, highthroughput simulations, and reasoningbased AI tools to guide discovery before materials are made in the lab. This approach focuses on understanding how a material’s atomic structure and electronic behavior determine properties such as magnetization strength, energy storage capacity, resistance to demagnetization, and performance at elevated temperatures. By embedding that physics knowledge into computational models, researchers can identify promising material candidates and reduce the need for experimental iteration. The challenge to making this approach effective is ensuring AI models are trained in the right kind of data. Rather than relying on generalized data, models must be trained on experimentally measured and scientifically calculated material properties to enable predictions that remain grounded in real-world behavior. By combining Ames’ strengths in theory, simulation, and proprietary magnetic materials data with emerging AI capabilities, researchers hope to expand the pace and scope of magnetic materials innovation. ameslab.gov. AM&P WINS TECHNICAL ARTICLE AWARD Advanced Materials & Processes (AM&P) magazine received some exciting feedback from the organizers of the 2026 Tabbie Awards conducted by Trade Association Business Publications International (TABPI). FEEDBACK We welcome all comments and suggestions. Send letters to joanne.miller@asminternational.org. AM&P won an Honorable Mention for Technical Articles! The winning article, “Post-Fire Metallurgical Assessment of Galvanized Anchors Supporting a Telecommunications Tower,” appeared in AM&P October 2025. Kudos to the authors, Dr. Mehrooz Zamanzadeh, FASM, Anil Kumar Chikkam, and our editorial team. Revisit the winning article here: static. asminternational.org/amp/202510/19. This is the fifth Tabbie recognition AM&P magazine has received since 2019. Physics-informed AI could accelerate discovery of new permanent magnets.
RkJQdWJsaXNoZXIy MTYyMzk3NQ==