BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:"Machine learning in chemistry and beyond" (ChE-651) seminar by Ju
 lian Zimmermann and Daniela Rupp "Machine learning based analysis of singl
 e-shot single-particle coherent diffraction imaging data"
DTSTART:20220426T151500
DTEND:20220426T161500
DTSTAMP:20261005T042010Z
UID:3975ffb1831c862871ffc699a22419d2c5e1667eec93426f7c2da668
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Daniela Rupp is a Tenure-Track Assistant Professor at th
 e head of the Nanostructures and Ultrafast X-ray Scienc group in the Depa
 rtment of Physics at ETHZ. Her group founded in 2019 develops and uses new
  methods to flash-image short-lived nanostructures and ultrafast changes i
 n their electronic and structural properties via diffraction imaging\, pus
 hing towards extreme time-resolution. Before that\, she was a Junior resea
 rch group leader in "Ultrafast dynamics in nanoplasma" at the Max Born Ins
 titute in Berlin\, Germany.\n\nShe will present her research together wit
 h Dr. Julian Zimmermann\, Postdoctoral researcher in her group at ETHZ.\n
 With the extremely intense short-wavelength pulses of X-ray free-electron 
 lasers (XFELs) and high harmonic sources (HHG) novel experiments with high
 est spatial and temporal resolution have become possible. One key example 
 is coherent diffraction imaging (CDI) of individual nanoparticles.\nHere\,
  the elastically scattered photons form an interference pattern that encod
 es the structural information of a single particle in a snapshot. An examp
 le of such a diffraction pattern is given in the figure. The CDI method al
 lows us to study such fragile structures as combustion aerosols or superfl
 uid helium nanodroplets and “film” ultrafast dynamics like laser induc
 ed melting in metal nanoparticles. But in order to retrieve the structural
  and dynamical information\, each pattern has to be decoded and a huge num
 ber of single diffraction patterns have to be analyzed. In that context\, 
 the tremendous progress of the last years in machine learning\, especially
  for pattern and image recognition tasks\, opens intriguing and long sough
 t pathways for diffraction imaging analysis. \nWe adapt and apply supervi
 sed and self-supervised deep neural networks for image classification and 
 similarity learning\, significantly reducing the manual analysis tasks. In
  our talk\, we will introduce the method of single-shot single-particle co
 herent diffraction imaging and explain the challenges we are facing and wh
 y they are calling for machine learning approaches. We will report on our 
 developed\, machine learning aided analysis pipeline and give an outlook o
 n current and future machine learning applications in coherent diffraction
  imaging.
LOCATION:https://epfl.zoom.us/j/64473017589?pwd=Vmpnd1pleGhEb1hFb3kxUlNIUW
 JyQT09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR