Toward Real-Time Analysis of Synchrotron Micro-Tomography Data: Accelerating Experimental Workflows with AI and HPC
- Virginia Tech, Blacksburg, VA
- ORNL
- University of New South Wales, Australia
- Oak Ridge National Laboratory (ORNL)
- University of Chicago
ynchrotron light sources are routinely used to perform imaging experiments. In this paper, we review the relevant computational stages, identify bottlenecks, and highlight future opportunities to streamline data acquisition for experimental microscopy workflows. We demonstrate our preliminary exploration with an end-to-end scientific workflow on Summit based on micro-computed tomography data. Computational elements include: 1) reconstruction of volumetric image data; 2) denoising with deep neural networks; and 3) non-local means based segmentation and quantitative analysis.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1855697
- Resource Relation:
- Journal Volume: 1315; Conference: Smoky Mountains Computational Sciences and Engineering Conference (SMC2020) - Kingsport, Tennessee, United States of America - 8/25/2020 8:00:00 AM-8/27/2020 8:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
Toward Real-Time Analysis of Synchrotron Micro-Tomography Data: Accelerating Experimental Workflows with AI and HPC
A workflow for segmenting soil and plant X-ray computed tomography images with deep learning in Google’s Colaboratory
Transitioning from File-Based HPC Workflows to Streaming Data Pipelines with openPMD and ADIOS2
Conference
·
Thu Jan 07 00:00:00 EST 2021
·
OSTI ID:1855697
+6 more
A workflow for segmenting soil and plant X-ray computed tomography images with deep learning in Google’s Colaboratory
Journal Article
·
Tue Sep 13 00:00:00 EDT 2022
· Frontiers in Plant Science
·
OSTI ID:1855697
+8 more
Transitioning from File-Based HPC Workflows to Streaming Data Pipelines with openPMD and ADIOS2
Conference
·
Tue Mar 01 00:00:00 EST 2022
·
OSTI ID:1855697
+9 more