BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241120T082409Z
LOCATION:HG E 1.1
DTSTART;TZID=Europe/Stockholm:20240605T100000
DTEND;TZID=Europe/Stockholm:20240605T103000
UID:submissions.pasc-conference.org_PASC24_sess113_msa188@linklings.com
SUMMARY:Advancing Soft Matter Structural Analysis: Closing the Discovery L
 oop with Neutron Scattering, Molecular Simulations, and Data Interpretatio
 n via Deep Learning
DESCRIPTION:Minisymposium\n\nWei-Ren Chen (Oak Ridge National Laboratory);
  Chi-Huan Tung (National Tsing Hua University); and Jan-Michael Carrillo, 
 Yangyang Wang, Changwoo Do, and Bobby Sumpter (Oak Ridge National Laborato
 ry)\n\nWe present our work on unveiling microscopic details of colloidal a
 nd soft matter systems through a novel integration of small-angle neutron 
 scattering (SANS), molecular simulations, computations, and machine learni
 ng (ML). First, we demonstrate how ML was employed to invert the scatterin
 g of charged colloidal particles to their relevant structural parameters. 
 Molecular dynamics simulations, a probabilistic Gaussian process framework
 , and a variational autoencoder were trained, and a trained decoder was it
 eratively applied to fit the input scattering experiment data, thereby clo
 sing the loop by transforming experimental SANS data into structural param
 eters. Similarly, we applied a methodology involving Monte Carlo simulatio
 ns of AB-type diblock copolymers with excluded volume effects at the dilut
 e limit, utilizing an ML framework of the Gaussian process to inversely de
 termine the conformation of these copolymers from their coherent scatterin
 g. Finally, we introduce our newly developed deep learning inversion frame
 work that employs convolutional neural networks to accurately extract morp
 hological features from a model lamella-forming system based on its SANS s
 pectra.\n\nDomain: Chemistry and Materials, Physics, Computational Methods
  and Applied Mathematics\n\nSession Chairs: Jan Michael Carrillo (Oak Ridg
 e National Laboratory) and Jihong Ma (The University of Vermont)
END:VEVENT
END:VCALENDAR