MISA Seminar (Apr. 5, 2022): "SWx TREC Deep Learning Laboratory Solar Flare Prediction Research and Hardware Capablilities"
Machine Intelligence for Space Applications (MISA) Seminar Series
Hosted by: CU's Space Weather Technology, Research, and Education Center (SWx TREC)
Presented by: Varad Deshmukh, Allison Liu, Kiera van der Sande, Steve Taylor, Harrison Bourne
Tuesday, April 5th 2022, 2:00pm – 3:00pm (MT)
Zoom recording: https://vimeo.com/699822293
In this talk, we will begin with presentations on student solar flare prediction research done within the SWx TREC Deep Learning Laboratory (DLL). Topics include:
- Creating a cohesive magnetogram dataset for solar flare prediction using Generative Adversarial Networks (GANs),
- Comparing solar flare irradiance in GOES X-ray and SDO/AIA EUV data via Machine Learning Regression, and
- ML-based solar flare prediction methodologies using SDO/HMI data, presenting flare prediction results using different ML modeling strategies and feature extraction methods.
The second set of presentations will be focused on the lab's hardware—the DLL has two Systems 76 workstations for machine learning research: one with an NVIDIA Titan RTX GPU card and 20 TB of local storage, and one with dual NVIDIA Titan V GPU cards and 85 TB of local HDD storage.