Solar spectropolarimetric inversions applying Deep Learning techniques | Juan Esteban Agudelo
Affiliation
Observatorio Astronómico Nacional de Colombia, Universidad Nacional de Colombia, Colombia
Main category
Natural Sciences (Astrophysics and Astrononmy)
Caption
Recent advancements in spectropolarimetric instrumentation, such as the new facilities at the GREGOR and DKIST telescopes, have generated vast amounts of data with each observation. This increase in data volume results in longer processing times, heightened demands on computational resources, and an expanded carbon footprint, complicating scientific development timelines. The numerical inversion codes used for data analysis, based on radiative transfer models, are inherently complex. Modern projects focused on the solar atmosphere and its magnetic field require additional assumptions, significantly increasing processing times for each pixel. To address this challenge, new methods are being developed, leveraging modern data processing algorithms from statistics and machine learning.
Further reading
Link to the European Solar Physics Online Seminars (ESPOS) webpage:
https://espos.stream/2024/10/31/Agudelo/
DOI
10.18147/smn.2024/video:374
If the video contains inappropriate content, please
report the video. You will be redirected to the landing page.