BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Accelerated Chemical Reaction Optimization using Multi-Task Learni
 ng
DTSTART:20231114T140000
DTEND:20231114T150000
DTSTAMP:20260501T112029Z
UID:6e69da44849a00f9f5c62e2a5786a1172e0c18c75312e95761aa6256
CATEGORIES:Conferences - Seminars
DESCRIPTION:Kobi Felton is a chemical engineer interested in solving probl
 ems at the intersection of chemical engineering\, chemistry and software. 
 He holds a Bachelor of Science in Chemical Engineering from North Carolina
  State University and a MPhil Research and PhD in Chemical Engineering fro
 m the University of Cambridge\, where he was a recipient of the Marshall S
 cholarship and the Cambridge-Marshall PhD Scholarship. His current projec
 ts include: Optimization of distillation control systems\, Self-optimizati
 on of reactions using bayesian algorithms\, Design of experiments for time
 -series datasets\, and Designing descriptors for chemical reactions.\nReac
 tion optimization is a standard challenge in process development that is o
 ften time- and labor-intensive. Recent work has shown that Bayesian optimi
 zation is an effective method for identifying optimal conditions\, yet it 
 can still be experimentally and materially expensive for reactions with ca
 tegorical selections (e.g.\, catalyst\, base). Ideally\, it would be possi
 ble to utilize the vast amount of data available in electronic lab noteboo
 ks to speed up optimization. In this talk\, we demonstrate that multi-task
  Bayesian optimization can accelerate reaction optimization by leveraging 
 historical data. We first conduct simulations to investigate the effective
 ness of multi-task Bayesian optimization\, showing that it can reduce the 
 number of experiments required to find optimal conditions by up to 80%. Fu
 rthermore\, we demonstrate the effectiveness of multi-task Bayesian optimi
 zation on an experimental case study of several related C-H activation rea
 ctions run in an automated flow chemistry reactor. Finally\, we study seve
 ral mechanisms by which multi-task Bayesian optimization can fail and prop
 ose mitigations.
LOCATION:https://epfl.zoom.us/j/68447908297?pwd=OU5JUGJUSUhZc0ZNYjQ2WENvYl
 NRdz09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR