ProgramMaster Logo
Conference Tools for MS&T21: Materials Science & Technology
Register as a New User
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Symposium
Meeting MS&T21: Materials Science & Technology
Symposium AI for Big Data Problems in Advanced Imaging, Materials Modeling and Automated Synthesis
Sponsorship TMS: Computational Materials Science and Engineering Committee
Organizer(s) Mathew J. Cherukara, Argonne National Laboratory
Badri Narayanan, University of Louisville
Subramanian Sankaranarayanan, University of Illinois (Chicago)
Scope 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:
• 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.

Abstracts Due 04/15/2021

A Deep Generative Model for Parametric EBSD Pattern Simulation
Aluminum Alloy Design Using Physics Informed Machine Learning
De Novo Inverse Design of Nanoporous Materials by Machine Learning
Deep Learning and Uncertainty Quantification for Automated Experiments
Discovery of Novel Crystal Structures via Generative Adversarial Networks
Machine Learning for Automated Experiment in Scanning Probe and Electron Microscopy
Machine Learning Polymer Property Prediction Models with Polymers Represented as Natural Language
Now On-Demand Only: Non-iterative Deep Learning for High-fidelity Microscopic Tomography
Optimizing the Training of Convolutional Neural Networks for Image Segmentation
Prediction of Dynamic Properties of LiF and FLiBe Molten Salts with DeepPot Network Potentials
Refinements to the Production of Machine Learning Interatomic Potentials
Semantic Segmentation of Porosity in In-situ X-ray Tomography Data Using FCNs
Tuning Optoelectronic Properties of Semiconductors with First Principles Modeling and Machine Learning
Understanding the Composition–property Relationship of Glasses Using Interpretable Machine Learning

Questions about ProgramMaster? Contact