We are aware that there is an unofficial third-party company offering to arrange accommodation and travel for your trip to Manchester. These emails are considered to be spam and should not be engaged with.

#INTERMAG2026

Speakers

Tutorial: AI and Magnetism

Peter Fischer

Lawrence Berkeley National Laboratory, Berkeley CA, USA

Title: AI in magnetism: Impact, Challenges and Risks – Addressing fundamental problems in magnetism research through artificial intelligence.

Abstract: In this tutorial I will introduce AI’s role in advancing magnetism research, I will cover some AI fundamentals, data requirements, and key challenges. I will highlight examples where AI accelerates discovery in magnetism and evaluate impacts, opportunities, and risks, empowering attendees to responsibly leverage AI in magnetic materials research.

Bio: Dr. Peter Fischer received his PhD in Physics (Dr.rer.nat.) from the Technical University in Munich, Germany in 1993 on pioneering work with X-ray magnetic circular dichroism in rare earth systems and his Habilitation from the University in Würzburg, Germany in 2000 based on his pioneering work on Magnetic Soft X-ray microscopy.

Since 2004 he is with the Material Sciences Division (MSD) at Lawrence Berkeley National Laboratory in Berkeley CA. He is the Division Director of MSD, Senior Scientist and Principal Investigator in the Non-Equilibrium Magnetic Materials Program. His research program is focused on the use of polarized synchrotron radiation for the study of fundamental problems in magnetism. Since 2014 he is also Adjunct Professor for Physics at the University of California in Santa Cruz.

Dr. Fischer has published so far over 240 peer reviewed papers and has given close to 370 invited presentations at national and international conferences. He was nominated as Distinguished Lecturer of the IEEE Magnetics Society in 2011. For his achievements of “hitting the 10nm resolution milestone with soft X-ray microscopy” he received the Klaus Halbach Award at the Advanced Light Source in 2010.

Dr. Fischer is Fellow of the APS and IEEE.

Cai-Zhuang Wang

Ames National Laboratory, IA, USA

Title: Accelerating discovery and synthesis of novel magnetic materials: Why and how AI/ML can help?

Abstract: In this tutorial talk, I will introduce some AI/ML methods/tools commonly used in materials research and review recent developments on leveraging AI/ML to dramatically speed up discovery and synthesis of novel magnetic materials, including our work at Ames National Laboratory. The power of integrating AI/ML with high-performance/exascale computing for significantly reducing the time-to-solution in novel materials discovery will be demonstrated. Examples on the discovery of high performance rare-earth free magnetic materials and novel complex quantum materials will be presented. Limitations of current ML approaches and challenges in closing the feedback loop between computational prediction and experimental synthesis will also be discussed.

Bio: Dr. Cai-Zhuang (CZ) Wang is a distinguished scientist at Ames National Laboratory and an adjunct professor at Department of Physics and Astronomy, Iowa State University, USA. He is also the lead PI (Director) of the USDOE-BES Computational Materials Science Center on Machine Learning Accelerated Materials Discovery. Dr. Wang’s research spans several areas in condensed matter theory and computational materials sciences. He has extensive expertise in modeling and simulation of materials at electronic and atomistic scales. He recently developed an efficient AI/ML-guided framework for accelerating the discovery, design, and synthesis of novel magnetic materials. Dr. Wang holds Physics degrees from University of Science and Technology of China (B.Sc., 1982), and Scuola Internazionale Superiore di Studi Avanzati (SISSA) in Italy (Ph.D., 1986). He was honored as a Fellow of the American Physical Society (APS) in 2014.

Gyorgy Csaba

Professor, Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Budapest, Hungary

Title: Magnonics for AI and AI for Magnonics

Abstract: This talk showcases the relationship between AI and magnonics from two perspectives. First, we show how machine-learning methods can boost the design of magnetic nanostructures, particularly magnonic devices. Second, we explore the potential of AI-designed magnonic systems for information-processing pipelines. AI-driven approaches gain ground in many areas of science, and we argue that magnonics is a particularly compelling area for their applications.

Bio: György Csaba is a professor at Pázmány Péter Catholic University in Budapest, Hungary, where he conducts research on unconventional computing devices. His main research interests include spin-based computing, such as magnonic signal processing, and other emerging computing paradigms, including oscillatory neural networks. He is one of the pioneers in applying machine learning techniques to the design of magnonic devices and works on leveraging these methods for future computing architectures and RF signal processing.

Masato Kotsugi

Professor, Faculty of Advanced Engineering, Tokyo University of Science

Title: Physics-Informed AI for Elucidating Magnetism: Extended Free Energy Framework

Abstract: This tutorial introduces a “Physics-Informed” AI framework designed to elucidate the complex mechanisms of magnetization reversal and energy loss in magnetic materials. While conventional AI often operates as a “black box,” our approach, the Extended Free Energy Framework (eX-GL), integrates topological data analysis with thermodynamic principles to provide explainable and causal insights. Targeting magnetism researchers with limited data science experience, this session will demonstrate how to construct energy landscapes in an information space using high-dimensional geometric features. We will explore the journey from theoretical design using micromagnetic simulations to practical applications in electrical steel for electric vehicles, illustrating how AI can visualize the invisible origins of coercivity and iron loss.

Bio: Masato Kotsugi is a Professor at the Tokyo University of Science and an expert in the intersection of magnetic microscopy and data science. His research leverages Explainable AI (XAI) to decode complex magnetic phenomena. He pioneered the “Extended Free Energy Framework (eX-GL),” a physics-informed AI approach that integrates thermodynamic principles with information geometry to visualize invisible energy landscapes in magnetic materials. By bridging material informatics and condensed matter physics, his work focuses on the causal analysis of coercivity and iron loss, contributing to the development of next-generation high-performance magnetic materials for green energy applications.