ProgramMaster Logo
Conference Tools for 2018 TMS Annual Meeting & Exhibition
Login
Register as a New User
Help
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting 2018 TMS Annual Meeting & Exhibition
Symposium Algorithm Development in Materials Science and Engineering
Presentation Title Deep Learning and Dynamic Sampling for Smart Data Acquisition in Scanning Electron Microscopy
Author(s) Yan Zhang, G. M. Dilshan Godaliyadda, Nicola Ferrier, Emine Gulsoy, Charles Bouman, Charudatta Phatak
On-Site Speaker (Planned) Charudatta Phatak
Abstract Scope In conventional point-based scanning modalities for imaging or spectroscopy, each pixel measurement can take up to a few seconds, which translates into several hours of data acquisition time for large image sizes. This is often true for energy-dispersive X-ray spectroscopy (EDX) in a scanning electron microscope (SEM) which is widely utilized in materials science for determining elemental compositions. In this work, we will present a dynamic sampling method based on supervised learning algorithm and convolutional neural networks for data acquisition in a SEM. We will demonstrate the results for two modalities: (1) secondary electron imaging, and (2) EDX mapping. Our method is capable of achieving high quality images and elemental maps with as low as 30% sampling from all available pixels. We will discuss the impact of various algorithms and the experimental implementation of these algorithms for smarter data acquisition resulting in reduced time and radiation exposure of the sample.
Proceedings Inclusion? Planned: Supplemental Proceedings volume

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Computational Framework for Predicting Failure Behavior of 2D Tin+1Cn Materials
A Dislocation-based Finite Element Modelling of Hydrogen Embrittlement in High-strength Steel Alloys
A New Method of Quantifying Solid-solution Hardening at Various Solute Concentrations Using Molecular Dynamics.
A Phase Field Study of Microstructure Evolution during Additive Manufacturing: Role of Temperature and Viscoplastic Attributes
Accelerated Quantum Molecular Dynamics
Accelerating Materials Simulation by Machine Learning
Algorithmic Extensions to Phase Field Dislocation Dynamics (PFDD) for Fcc and Bcc metals
Algorithms to Simulate the Structure and Mobility of Nanoscale Dislocation Shear Loops via Atomistic Simulations
An Explicit Methodology for Hierarchical Bridging between Ab Initio and Atomistic Scales
Assessment of Heterogeneous Elastic Strains in Polycrystalline Ti-5Al-2.5Sn and Modeling with Taylor Gradient Enhanced Phenomenological Crystal Plasticity Model
Atomistic Cross-scale Simulations of Crystal Plasticity
Atomistically-informed Chemistry Models for Thermo-chemical Degradation of Ablative Composite Materials
Automated Calculation of First-principles Based Diffusion Coefficients in Non-dilute Alloys
Computational Performance of Phase Field Calculations using a Matrix-free (Sum-Factorization) Finite Element Method
Computational Phonon Manipulation
Computing the Lattice Green Function in Complex Materials
Concepts, Data Bases and Analysis Tools for Dislocation Micro Structures Across the Length Scales
Crack-tip Simulation Validations by XGP Multiscale Methods
Data Fusion and Mining of In Situ Monitoring Sensors, Process Modeling, and Defect Characterization in Powder Bed Fusion Additive Manufacturing
Deep Learning and Dynamic Sampling for Smart Data Acquisition in Scanning Electron Microscopy
Developing a Workflow for Process-structure-property Linkage through Monte Carlo and Direct Numerical Simulations
Development and Parameterization of Phase-field-crystal Models
Discrete Dislocation Dynamics Based Polycrystal Plasticity
Divergent Properties from Divergent Microstructures: The Effect of Polycrystal Instantiation Methods on Macroscopic Materials Properties.
GPU Accelerated Phase Field Dislocation Dynamics: Application to Bi-metallic Interfaces
Hierarchical Simplex Sampling: An Efficient Algorithm for Construction of Diverse Microstructural Sets and Delineation of Properties Closures
High-throughput Evaluation and Comparison of Classical Interatomic-potentials: Structural, Elastic, Defect, Surface and Phonon Properties
Integrating Molecular Dynamics and Phase-Field Modeling to Study Oxidation of Iron
Large-scale Real-space Electronic Structure Calculations
MSGalaxy: A Web-based Platform for Framework Design and Integration.
Open Source Distributed Tools for Multiscale Modeling of Materials
Ordering and Properties of Pure and Binary Two Dimensional Honeycomb Films
Parallel Algorithms for Hyperdynamics in LAMMPS
Plastic Material Spin in Atomistic Simulations
Plasticity Analysis in Molecular Dynamics via Simple Shear Field Decomposition
PyCAC: The Concurrent Atomistic-continuum Simulator with a Python Scripting Interface
Rational Design and Parametric Uncertainty Analysis of Classical Interatomic Potentials
Reactive Molecular Dynamics of Electrochemical Processes – Ultrafast Resistance Switching in Electro-metallization Cells
Recent Advances in Polycrystal Plasticity Models and Algorithms: FFT-based and Self-consistent Approaches
Segmentation for Large Datasets of X-ray Microscopes by Using a Deep Convolutional Neural Network
Simulation of multi-component microstructure evolution coupling phase field and tensor decomposition techniques
Structural Characterizations of Fine Nb Wires in Superconducting Integrated Circuits
Three-dimensional Structure and Motion of Defect Loops on the {10-12} Twin Boundary in Magnesium
Three Dimensional Trefftz Voronoi Cell Finite Elements with Cylindrical Elastic/Rigid Inclusions &/or Voids for Micromechanical Modeling of Heterogeneous Materials
Transition State Redox during Dynamical Processes in Semiconductors and Insulators
Using Machine-learning to Create Predictive Material Property Models

Questions about ProgramMaster? Contact programming@programmaster.org