BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Machine Learning methods for solar spectroscopy and imaging
DTSTART;VALUE=DATE-TIME:20230512T081000Z
DTEND;VALUE=DATE-TIME:20230512T083500Z
DTSTAMP;VALUE=DATE-TIME:20240704T115655Z
UID:indico-contribution-354@meetings.aip.de
DESCRIPTION:Speakers: Andrés Asensio Ramos (Instituto de Astrofísica de 
 Canarias)\nSolar spectropolarimetry is entering the realm of big data. Cur
 rent and future telescopes will produce data at a rate that will make it h
 ard to store in a single machine and even harder to operate on the data. T
 hankfully\, in the last decade\, machine learning has experienced an enorm
 ous advance\, thanks to the open possibility of training very deep and com
 plex neural networks. In this \ncontribution I show options to explore to 
 deal with the big data problem and also how deep learning can be used to e
 fficiently solve difficult problems in Solar Physics. I will focus on how 
 differentiable programming (aka deep learning) is helping us to have acces
 s to velocity fields in the solar atmosphere\, correct for the atmospheric
  degradation of spectropolarimetric data and carry out fast 3D inversions 
 of the Stokes parameters to get physical information of the solar atmosphe
 re.\n\nhttps://meetings.aip.de/event/24/contributions/354/
LOCATION:Haus H\, Telegrafenberg
URL:https://meetings.aip.de/event/24/contributions/354/
END:VEVENT
END:VCALENDAR