||There have been increasing efforts in exploring data-driven decision making and machine-learning augmented approaches for efficient materials design. An exciting recent progress is integrating these data-driven and machine-learning approaches with advanced characterization tools, such as advanced electron microscopy and synchrotron analysis, to access and to predict critical processing-structure-property relationships. The design of nano-architectured materials exhibits a complex parameter space, and thus the community could profit from applying and further developing these novel methodologies to avoid the ‘trial-and-error’ approach and to complement computational simulations and theoretical analyses.
This special symposium session thus aims to gather experts on the critical emerging topic of data-driven, machine-learning-based nano-architectured materials design. It will also place a key emphasis on novel characterization, such as autonomous synchrotron X-ray characterization and data-driven next generation transmission electron microscopy. The event will be a special session in conjunction with the regular symposium, “Self-organizing Nano-architectured Materials”. The session is intended to be interdisciplinary, covering a range of materials, such as metallic nanomaterials, self-assembling block copolymers, combinatorial thin films and electronic, magnetic and smart materials. This session will provide a forum for seemingly disparate fields to interact and drive materials discovery with novel characterization methods that are augmented by data science and machine learning.