BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Autonomous research machines: Self-optimizing new 
 chemistry - Ruth Misener (Imperial College London)
DTSTART;TZID=Europe/London:20230424T113000
DTEND;TZID=Europe/London:20230424T123000
UID:TALK198394AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/198394
DESCRIPTION:Our research seeks to boost R&D efficiency in the 
 chemicals industry. As an example\, consider "micr
 o reactor flow systems"\, which are transforming c
 hemical manufacturing by enabling flexible prototy
 ping. Because these high-throughput microfluidic d
 evices can control reaction conditions online\, th
 ey are ideal for quantitatively characterizing div
 erse chemical synthesis techniques along new react
 ion pathways. The challenge is: How do we automate
  the design of experiments to "self-optimise" new 
 chemistry? Together with the BASF Data Science for
  Materials & Chemistry teams\, we&rsquo\;re intere
 sted to solve Bayesian optimization challenges whi
 ch may simultaneously exhibit: multiple objectives
 \, mixed-feature spaces\, asynchronous decisions\,
  large batch sizes\, input constraints\, multi-fid
 elity observations\, hierarchical choices\, and co
 sts associated with switching between experimental
  points. We review the machine learning contributi
 ons that we&rsquo\;ve found useful towards achievi
 ng these goals and discuss our own methodological 
 and software contributions.\nThis work is a collab
 oration between Imperial (Jose Pablo Folch\, Alexa
 nder Thebelt\, Shiqiang Zhang\, Jan Kronqvist\, Ca
 lvin Tsay\, Ruth Misener) and BASF (Robert Lee\, B
 ehrang Shafei\, Nathan Sudermann-Merx\, David Walz
 ).
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:
END:VEVENT
END:VCALENDAR