BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY: Machine learning aided fast and accurate quantum chemistry for so
 lvated molecules - Prof Fang Liu\, Emory University
DTSTART:20230306T143000Z
DTEND:20230306T150000Z
UID:TALK197854@talks.cam.ac.uk
CONTACT:Dr Christoph Schran
DESCRIPTION: The fast and accurate description of the solvent environment 
 is crucial for quantum chemical (QC) discovery in the solution phase. We c
 ombine high-performance computing hardware and machine learning (ML) techn
 iques to improve the efficiency and accuracy of QC discovery of solvated m
 olecules.  \n\nTo improve the efficiency\, we developed strategies to acce
 lerate both the implicit and explicit solvent models. For the implicit sol
 vent models such as the conductor-like polarization model (C-PCM)\, we exp
 loited graphical processing units (GPUs) to accelerate the calculation and
  achieved hundreds of speedups for ground- and excited- state calculations
 . For the explicit solvent model\, we developed AutoSolvate\, an open-sour
 ce toolkit to streamline the QC calculation workflow of explicitly solvate
 d molecules.  To improve the accuracy\, we develop ML models to reduce the
  discrepancy between experimental measurements and computationally predict
 ed molecular properties in both implicit and explicit solvent models. For 
 ground-state redox potential calculations\, our ML models can reduce both 
 the systematic bias and the number of outliers\, and the ML corrected resu
 lts demonstrate less sensitivity to density functional theory (DFT) functi
 onal choice. This ML correction technique is transferrable to predicting o
 ther molecular properties in the solution phase\, including the excited st
 ate redox potential and absorption/fluorescence wavelength.
LOCATION:Zoom link: https://zoom.us/j/92447982065?pwd=RkhaYkM5VTZPZ3pYSHpt
 UXlRSkppQT09
END:VEVENT
END:VCALENDAR