BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Classification Scheme for High-resolution Spectra Using Machine Le
 arning Algorithms
DTSTART;VALUE=DATE-TIME:20230512T074000Z
DTEND;VALUE=DATE-TIME:20230512T075500Z
DTSTAMP;VALUE=DATE-TIME:20240704T115655Z
UID:indico-contribution-349@meetings.aip.de
DESCRIPTION:Speakers: Ekaterina Dineva (Katholieke Universiteit Leuven)\nC
 ontemporary solar physics deals with increasing volumes of high-dimensiona
 l data from observations and realistic theoretical models alike. Machine L
 earning (ML) is rapidly integrated into solar and heliophysics research\, 
 facilitating dimensionality reduction\, visualization and analysis. We dev
 eloped a pipeline\, which employed carefully selected unsupervised ML algo
 rithms for classification and cluster analysis\, to extract information re
 garding the physical properties of the solar atmosphere contained in the l
 arge variety of spectral profiles. The pipeline is tested on the synthetic
  spectra of the Fe I $\\lambda\\\,7090.38$ Å photospheric absorption line
 \, computed with the CO$^5$BOLD radiation hydrodynamics code. This line is
  also part of the observing setup for the Fast Multi-line Universal Spectr
 ograph (FaMuLUS) camera system at the Vacuum Tower Telescope (VTT). CO$^5$
 BOLD snapshot time-series serve as a simulation of high-resolution\, fast-
 cadence solar observations\, thus confronting the pipeline with the scenar
 io of dynamic solar feature evolution. This project aims to deliver a robu
 st classification scheme with minimal user interaction\, which also prepar
 es the spectral dataset for further analysis\, such as spectral inversions
 . Successful classification allows quick identification of structure and d
 ynamics in the region of interest\, as well as diagnostics of the ambient 
 plasma based on spectra line parameters.\n\nhttps://meetings.aip.de/event/
 24/contributions/349/
LOCATION:Haus H\, Telegrafenberg
URL:https://meetings.aip.de/event/24/contributions/349/
END:VEVENT
END:VCALENDAR