Published December 1, 2023 | Version v1
Poster Open

Advancing Heliophysics Data Analysis through Machine Learning: Utilizing Yolov7 for Cataloging of SOHO/LASCO C2 Images

Authors/Creators

  • 1. ROR icon National Aeronautics and Space Administration

Contributors

  • 1. ROR icon Goddard Space Flight Center
  • 2. ROR icon Georgia State University

Description

At a Glance:

  • Computer Vision (CV), a form of Machine Learning (ML), can successfully detect CME in solar images (SOHO/LASCO C2).

  • A leading COTS ML model is YOLO which can be applied to extract physical metrics of CME.

  • YOLO (v7) detected CME regions and associated physical metrics compare favorably with human selected regions (and metrics).

Files

B Thomas AGU2023 CME ML Poster.pdf

Files (4.3 MB)

Name Size Download all
md5:6ed10e505c729ef99934af30f5ba2a50
4.3 MB Preview Download

Additional details

Funding

National Aeronautics and Space Administration
Using Machine Learning to Detect and Build CME Datasets for Heliophysics NNH21ZDA001N-LWSTM

Dates

Accepted
2023-12-01
AGU poster