|About this Symposium
||MS&T22: Materials Science & Technology
||AI for Big Data Problems in Advanced Imaging, Materials Modeling and Automated Synthesis
||TMS Advanced Characterization, Testing, and Simulation Committee
||Mathew Cherukara, Argonne National Laboratory
Subramanian Sankaranarayanan, University of Illinois-Chicago
Badri Narayanan, University of Louisville
||The advent of big data analytics in computer science along with the reduction in computing and memory costs over the last few years have brought powerful machine learning (ML) techniques to the forefront; such methods are now routinely used in business, transactional and social media applications. In particular, the rise of deep neural networks or deep learning (DL) over the last 3-5 years has revolutionized the fields of computer vision, mechanical automation and natural language processing to name a few. In the physical sciences, deep learning methods have been employed to accelerate data analysis for time-resolved X-ray and electron imaging, to design new molecular structures, to automate manufacturing and even accelerate the materials design loop. This workshop aims to bring together experimental and theoretical experts in applied AI from academia, national labs and industries to discuss the latest developments in machine learning tools and techniques to develop new methods to accelerate design, discovery, synthesis and characterization for a range of different emerging energy applications and technologies.
Focus areas include:
• Digital Twins for spatiotemporal experiments and materials design
• Quantum machine learning
• Autonomous systems and experimentation
• Edge computing and edge characterization
• Deep learning approaches to solve inverse problems in imaging including coherent imaging methods, tomographic methods and Lorentz TEM.
• Deep learning methods for automated feature detection and labeling in X-ray and electron imaging, including ultra-fast imaging.
• Machine learning and data mining for property prediction and inverse design of materials.
• Automatic differentiation applied to inverse problems in characterization.
• AI enabled feedback and experimental/instrumentation control.
• Machine learning techniques to bridge length scales in materials modeling.
• Generative AI for novel material and chemical synthesis.
• Reinforcement learning (RL) to guide simulation/experiment.